data/coding/genesis_code_10k/shard-00000.jsonl

{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: design\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: Bash\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Extended context and repo-scale understanding\nDifficulty: foundation\nTarget language: Bash\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: eval\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: foundation\nTarget language: SQL\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: SQL\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: C#\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: C#\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: Go\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: eval\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: C#\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: Python\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: eval\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: Rust\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: explain\nTopic: Secure code generation and policy gates\nDifficulty: foundation\nTarget language: SQL\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: eval\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: Python\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: Python\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: eval\nTopic: Governance, provenance, and licensing for code data\nDifficulty: foundation\nTarget language: Rust\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: Rust\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: compare\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: Rust\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: foundation\nTarget language: TypeScript\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: foundation\nTarget language: TypeScript\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: compare\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: foundation\nTarget language: Rust\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: Python\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: SQL\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: Rust\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: explain\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: Go\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: SQL\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: design\nTopic: Agentic coding systems (plan→edit→test→reflect)\nDifficulty: intermediate\nTarget language: Bash\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: Java\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: Rust\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Agentic coding systems (plan→edit→test→reflect)\nDifficulty: expert\nTarget language: Java\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: C#\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: Java\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Agentic coding systems (plan→edit→test→reflect)\nDifficulty: intermediate\nTarget language: C#\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: TypeScript\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: foundation\nTarget language: Go\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: explain\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: JavaScript\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: eval\nTopic: Agentic coding systems (plan→edit→test→reflect)\nDifficulty: foundation\nTarget language: Rust\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: compare\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: Python\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: Rust\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Secure code generation and policy gates\nDifficulty: foundation\nTarget language: Python\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: C#\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: Rust\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: JavaScript\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: JavaScript\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: JavaScript\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: Rust\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: design\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: Go\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: TypeScript\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: design\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: compare\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: Rust\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: design\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: Bash\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: foundation\nTarget language: Java\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: design\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: foundation\nTarget language: TypeScript\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Agentic coding systems (plan→edit→test→reflect)\nDifficulty: expert\nTarget language: Rust\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: foundation\nTarget language: JavaScript\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: Python\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: eval\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: foundation\nTarget language: Java\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: compare\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: Go\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: foundation\nTarget language: JavaScript\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: Python\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: C#\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: Go\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: Bash\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: Bash\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: design\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: Java\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: Rust\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: design\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: foundation\nTarget language: Java\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: eval\nTopic: SWE-bench style real-repo evaluation\nDifficulty: foundation\nTarget language: Rust\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: eval\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: Go\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: C#\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: eval\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: foundation\nTarget language: JavaScript\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: explain\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: Rust\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: Java\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: foundation\nTarget language: C#\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: compare\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: TypeScript\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: compare\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: Go\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: eval\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: Rust\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: design\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: Java\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: design\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: TypeScript\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: Go\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Secure code generation and policy gates\nDifficulty: foundation\nTarget language: C#\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: compare\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: Java\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: eval\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: Python\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: eval\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: C#\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: explain\nTopic: Agentic coding systems (plan→edit→test→reflect)\nDifficulty: expert\nTarget language: Bash\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: compare\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: foundation\nTarget language: Go\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: foundation\nTarget language: Python\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Agentic coding systems (plan→edit→test→reflect)\nDifficulty: expert\nTarget language: Python\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: eval\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: compare\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: Bash\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: Java\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: Go\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: compare\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: foundation\nTarget language: Rust\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: TypeScript\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: design\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: Go\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: C#\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: explain\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: Python\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: C#\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: design\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: SQL\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Governance, provenance, and licensing for code data\nDifficulty: foundation\nTarget language: Go\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: SQL\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: explain\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: TypeScript\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Python\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: design\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: C#\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: Java\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: Bash\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: Rust\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: C#\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: Bash\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: Go\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: explain\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: Go\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: design\nTopic: Governance, provenance, and licensing for code data\nDifficulty: foundation\nTarget language: Rust\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: Python\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: Rust\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: Go\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: C#\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: JavaScript\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: compare\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: Java\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: compare\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: Python\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReference scaffold:\n```python\ndef agent_loop(plan, edit, test, issue, max_iters=3):\n    history = []\n    p = plan(issue)\n    for _ in range(max_iters):\n        patch = edit(issue, p)\n        ok, report = test(patch)\n        history.append({\"plan\": p, \"passed\": ok, \"report\": report[:200]})\n        if ok:\n            return patch, history\n        p = p + \" | refine from failures\"\n    return patch, history\n\n```\nOperational notes: sandbox, pinned deps, human gate.", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: foundation\nTarget language: JavaScript\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Extended context and repo-scale understanding\nDifficulty: foundation\nTarget language: Go\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: eval\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: explain\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: Rust\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: explain\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: C#\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: compare\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: TypeScript\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: Go\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: eval\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: intermediate\nTarget language: Python\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Agentic coding systems (plan→edit→test→reflect)\nDifficulty: advanced\nTarget language: Rust\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Agentic coding systems (plan→edit→test→reflect)\nDifficulty: advanced\nTarget language: Java\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: design\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: explain\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: foundation\nTarget language: SQL\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: JavaScript\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: eval\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: TypeScript\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: compare\nTopic: Secure code generation and policy gates\nDifficulty: foundation\nTarget language: JavaScript\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: JavaScript\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: eval\nTopic: Agentic coding systems (plan→edit→test→reflect)\nDifficulty: advanced\nTarget language: Go\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: advanced\nTarget language: JavaScript\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: C#\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: design\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: foundation\nTarget language: C#\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: TypeScript\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Agentic coding systems (plan→edit→test→reflect)\nDifficulty: advanced\nTarget language: C#\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: explain\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: Python\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: foundation\nTarget language: Go\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: compare\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: TypeScript\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: design\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Bash\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: eval\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: Java\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: compare\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: foundation\nTarget language: Java\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: design\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Python\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: Python\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: Bash\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: explain\nTopic: Agentic coding systems (plan→edit→test→reflect)\nDifficulty: foundation\nTarget language: C#\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: explain\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: Go\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: C#\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: design\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: foundation\nTarget language: Rust\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: foundation\nTarget language: Java\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Secure code generation and policy gates\nDifficulty: foundation\nTarget language: Java\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: JavaScript\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Governance, provenance, and licensing for code data\nDifficulty: foundation\nTarget language: Java\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: Go\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: compare\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: Bash\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: foundation\nTarget language: Python\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReference scaffold:\n```python\ndef agent_loop(plan, edit, test, issue, max_iters=3):\n    history = []\n    p = plan(issue)\n    for _ in range(max_iters):\n        patch = edit(issue, p)\n        ok, report = test(patch)\n        history.append({\"plan\": p, \"passed\": ok, \"report\": report[:200]})\n        if ok:\n            return patch, history\n        p = p + \" | refine from failures\"\n    return patch, history\n\n```\nOperational notes: sandbox, pinned deps, human gate.", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: explain\nTopic: Agentic coding systems (plan→edit→test→reflect)\nDifficulty: intermediate\nTarget language: Bash\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: design\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: Rust\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Extended context and repo-scale understanding\nDifficulty: foundation\nTarget language: Bash\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: Go\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: explain\nTopic: Extended context and repo-scale understanding\nDifficulty: foundation\nTarget language: SQL\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Agentic coding systems (plan→edit→test→reflect)\nDifficulty: advanced\nTarget language: TypeScript\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: Rust\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: TypeScript\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: Rust\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: Bash\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: compare\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: foundation\nTarget language: Go\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: explain\nTopic: Extended context and repo-scale understanding\nDifficulty: foundation\nTarget language: C#\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: SWE-bench style real-repo evaluation\nDifficulty: foundation\nTarget language: SQL\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: explain\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: expert\nTarget language: TypeScript\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Agentic coding systems (plan→edit→test→reflect)\nDifficulty: foundation\nTarget language: Java\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: intermediate\nTarget language: Go\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: Go\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: eval\nTopic: Agentic coding systems (plan→edit→test→reflect)\nDifficulty: advanced\nTarget language: Rust\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: data_pipeline\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: C#\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Agentic coding systems (plan→edit→test→reflect)\nDifficulty: intermediate\nTarget language: Python\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: JavaScript\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: explain\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: foundation\nTarget language: C#\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: agent_loop\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: foundation\nTarget language: Go\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan → Edit (diff) → Test → Reflect → Human gate\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Secure code generation and policy gates\nDifficulty: foundation\nTarget language: SQL\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: design\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: Bash\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Extended context and repo-scale understanding\nDifficulty: foundation\nTarget language: TypeScript\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: review\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: SQL\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: explain\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: C#\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: code\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: Python\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReference scaffold:\n```python\ndef agent_loop(plan, edit, test, issue, max_iters=3):\n    history = []\n    p = plan(issue)\n    for _ in range(max_iters):\n        patch = edit(issue, p)\n        ok, report = test(patch)\n        history.append({\"plan\": p, \"passed\": ok, \"report\": report[:200]})\n        if ok:\n            return patch, history\n        p = p + \" | refine from failures\"\n    return patch, history\n\n```\nOperational notes: sandbox, pinned deps, human gate.", "category": "coding"}
{"source": "genesis_code_10k", "source_dataset": "WithinUsAI/Genesis_AI_Code_10k", "instruction": "Task: eval\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: Python\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "response": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "category": "coding"}