messages list | tier int64 | src string | verified bool |
|---|---|---|---|
[
{
"role": "user",
"content": "…[earlier truncated]…\nsage.slice(0,40) + ')'); else { console.log(f, 'FAIL', e.message); process.exit(1); } }\\n}\\\"\", \"description\": \"Parse-check all modified modules\"}\nResult: renderer OK\ngame OK\nsettings OK\nmaps OK\naudio OK\nAssistant action: Edit {\"replace_all\... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n file C:\\Users\\user\\CascadeProjects\\3d-render\\index.html has been updated successfully. (file state is current in your context — no need to Read it back)\nAssistant action: Edit {\"replace_all\": false, \"file_path\": \"C:\\\\Users\\\\aranr\\\\Cascad... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n First code task should establish the config module (docs/rules/process.md, configuration section) and the first docs/functions.md entries.\n\n## [2026-06-09 17:18] — scaffolding verification\n\n**TL;DR:** All Makefile targets verified. `make lint` initia... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": " USE_FAST_ACCUM=False, num_stages=4, num_warps=8\nSingleProcess AUTOTUNE benchmarking takes 0.2880 seconds and 0.0001 seconds precompiling for 18 choices\nAssistant action: Bash {\"command\": \"grep -E 'compiled bs|tok/s' /tmp/claude-1000/-home-lane-MythosMini/2939e800-ac05-471... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "I'm lazy and looking for best practices for a blog post where I need to build a real-time notification system with WebSockets and fallback. I'm a game developer using Go and Django. I need to understand the approach. What's your heuristic for this? Also, How do you handle the r... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nresolveAndMaybeBlockOnLoaderThread (node:internal/modules/esm/loader:730:38)\n at ModuleLoader …[truncated]\nAssistant action: Bash {\"command\": \"ls ~/.claude/skills/paperclip-dev/ && head -100 ~/.claude/skills/paperclip-dev/SKILL.md\", \"description... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n data: BenchmarkData,\n185\t eval_batch: int,\n186\t info: DeviceInfo,\n187\t leaderboard: list[LeaderboardEntry],\n188\t parameter_count: int,\n189\t) -> MergeCandidate:\n190\t best_seed = select_diverse(candidates, 1)[0]\n191\t print(\... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "As a researcher documenting how experts solve problems, i'm a game developer for a side project. I'm paranoid about edge cases about a terminal task: debug a Docker container that crashes with exit code 137 on startup using docker logs and docker exec. What I can't figure out: ... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "user",
"content": "You are tasked with implementing a URL routing system for a web application. Given a list of URL patterns, each represented as a tuple containing a regular expression pattern and a name for the URL pattern, create a function that takes a URL and matches it to the corresponding ... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that calculates the initial position of a game character based on its movement direction and speed. The function takes four parameters: `screen_width` (an integer representing the width of the screen), `moveDir` (an integer where 1 me... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "Given a list of integers `wdata` and an integer `w`, your task is to calculate the amplitude for each contiguous subset of size `w`. The amplitude of a subset is defined as the difference between the maximum and minimum values in that subset. You need to implement a function `c... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n\t mastered = (drops > threshold) & (current < floor)\n69\t return ~mastered\n70\t\n71\t\n72\tdef stm_epoch(\n73\t model: MythosMini,\n74\t optimizer: torch.optim.NAdam,\n75\t pool: Tensor,\n76\t indices: Tensor,\n77\t config: StmConf... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nd it back)\nAssistant action: Bash {\"command\": \".venv/bin/python -m pytest tests/test_sparse_attention.py -q 2>&1 | tail -15\", \"description\": \"Run sparse attention tests\"}\nResult: ............ ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": " \nstep 3051 skipped: non-finite grad norm (inf) \nstep ... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "token cap after the fix pass, or leave them?\nUser: <local-command-caveat>Caveat: The messages below were generated by the user while running local commands. DO NOT respond to these messages or otherwise consider them in your response unless the user explicitly asks you to.</lo... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": " <option value=\"wiki\">WikiText-2 PPL</option>\n717: <option value=\"arc\">ARC-Easy</option>\n734: <th class=\"cell-metric\">WikiText-2 ↓</th>\n766: <canvas id=\"arcChart\"></canvas>\n769: <h3>WikiText-2 Perplexity ↓</h3>\n770: ... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "Make this UI mobile freindly\nAssistant action: Bash {\"command\": \"ls /home/user/Blindbot/hf_space\", \"description\": \"List hf_space files\"}\nResult: app.py\nDockerfile\n__pycache__\nrequirements.txt\nstatic\nAssistant action: Bash {\"command\": \"ls /home/user/Blindbot/hf... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": ".3M/2.00G [00:16<12:12, 2.67Mtok/s]\rtraining: 2%|▏ | 46.0M/2.00G [00:17<12:11, 2.67Mtok/s]\rtraining: 2%|▏ | 48.8M/2.00G [00:18<12:09, 2.67Mtok/s]\rtraining: 3%|▎ | 51.6M/2.00G [00:19<12:05, 2.68Mtok/s]\rtraining: 3%|▎ | 54.5M/2.00G [00:... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that simulates the transactions of a simple bank account. The function should take an initial balance, a list of deposit amounts, and a list of withdrawal amounts. It should calculate the final balance after processing all the deposit... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "1. The save configuration button is glitchy on the setup page.\n2. The logo has a white background for some reason, just use the transparent background svg.\n3. I just launched teich studio and tried starting an interactive claude-code session. The container is live but the ter... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with calculating the total payroll for a list of different types of employees in a company. Each employee has specific attributes that determine their payroll amount. You need to implement a function `calculate_total_payroll(employees: List[Dict[str, Union[str, i... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a data engineer. Focus on correctness, performance, and scalability."
},
{
"role": "user",
"content": "What is a data lake vs a data warehouse?"
},
{
"role": "assistant",
"content": "# Data Lake vs Data Warehouse\n\n## Data Lake\nA centralized ... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are given a 9x9 Sudoku grid represented as a 2D list of integers, where each integer is between 0 and 9. Your task is to implement a function `check_sudoku_squares(grid)` that validates the accuracy of the Sudoku grid by checking if each 3x3 subgrid (or square) contains the... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function that computes the Weighted Hausdorff Distance Regression (WHDR) Hinge loss for semantic segmentation tasks. The function should take the following parameters: \n\n- `delta` (float): A parameter for the WHDR loss function. Default valu... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that validates a dictionary representing logging configuration settings. The function should ensure that the configuration contains a 'logging' key and that its value is a dictionary. If the configuration is valid, the function sho... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "paperclip should not be using the GPU. Please properly kill it and test the outputs of the new model.\nAssistant action: Skill {\"skill\": \"paperclip\", \"args\": \"pause the Glint Research company / lead_architect agent so it stops using the GPU\"}\nResult: Launching skill: p... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are given a 2D list of rotation vectors, where each inner list represents a rotation vector in a batch. Your task is to calculate the average magnitude of these rotation vectors using the Euclidean norm. Write a function `average_magnitude(rot_vecs: List[List[float]]) -> fl... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "[Image: source: /home/user/.claude/image-cache/602033e7-dc55-4b7f-909f-1c67135d8f4b/1.png]\nAssistant action: Bash {\"command\": \"ps aux --sort=-%mem | head -12; free -h | head -2\", \"description\": \"See what is climbing\"}\nResult: USER PID %CPU %MEM VSZ RSS TT... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "can you change the building UI to be more Robloxy?\nAssistant: Studio gets the full pro-editor treatment — all original design, generic editor conventions: ribbon toolbar with grouped tools, Explorer scene-tree panel, real 3D move/scale gizmos with colored axis handles, snap co... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nt-cli/src/components/Input.tsx\", \"content\": \"import React, { useState } from \\\"react\\\";\\nimport { Text, useInput } from \\\"ink\\\";\\nimport { theme } from \\\"../theme.ts\\\";\\n\\ninterface InputProps {\\n onSubmit: (value: string) => void;\\... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\ntf8\\\");\\nconst physicsSrc = html.slice(html.indexOf(\\\"const FLUID\\\"), html.indexOf(\\\"const SPLAT_VS\\\"));\\nconst FlipFluid = new Function(physicsSrc + \\\"\\\\nreturn FlipFluid;\\\")();\\n\\nconst fluid = new FlipFluid(3.0 * 1.77, 3.0, 64, 3000... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are an experienced Elixir/OTP architect. Discuss supervisor design with practical specifics: restart strategies, child specs, failure isolation, and the trade-offs that real production systems hit. Assume the user is comfortable with basic GenServer code."
},
{
"r... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that processes a dataset of housing attributes represented as a list of lists. Each inner list contains the following attributes in the specified order: 'CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD', 'TAX', 'PTRAT... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": " POST \\\"http://localhost:3100/api/agents/$AID/wake\\\" -H \\\"Content-Type: application/json\\\" -d '{\\\"source\\\":\\\"on_demand\\\",\\\"reason\\\":\\\"smoke test: reply with one word OK\\\"}'; echo\", \"description\": \"Wake Groq agent for smoke test\"}\nResult: {\"error\"... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a function that processes a list of numbers. The function should accept a list of integers as input, append the numbers 5 and 2 to the list, sort the modified list in ascending order, and return a new list containing the square of each number from t... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nmax_retries=0, # retries are handled explicitly below\n27\t )\n28\t\n29\t\n30\tdef build_image_content(base64_images: list[str]) -> list[dict[str, Any]]:\n31\t \"\"\"Build the content array with interleaved images for the vision API.\"\"\"\n32\t ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nlexShrink={0}>\\n <Text color={theme.orange}>✦</Text>\\n </Box>\\n <Box flexDirection=\\\"column\\\" flexGrow={1}>\\n <Markdown text={item.text} />\\n </Box>\\n </... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "Add them please\nAdd them please (excluding distributed training)"
},
{
"role": "assistant",
"content": "<think>\nAlright, the user just asked: “Add them please (excluding distributed training)”. They’re referring to the list of ideas I just summarized from the Disc... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with calculating the remaining area to be painted on a wall after accounting for a percentage of the wall area that is not to be painted. Write a function `calculate_remaining_area(wall_width: int, not_painted_percentage: int) -> int` that takes the width of the ... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a TypeScript expert who explains advanced type system mechanics with working code. Always check that examples compile under strict mode."
},
{
"role": "user",
"content": "I've been fighting this for an hour. I have a function that takes a discriminated uni... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "As a helpful assistant, i'm skeptical and critical for a technical documentation because blood test results came back with hemoglobin 11.2, ferritin 15, B12 180. I'm a junior developer trying to figure out what can I safely read into these before talking to my doctor. Where's t... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nle /home/user/AIArchives/archives/neonstrike/app/public/js/main.js has been updated successfully. (file state is current in your context — no need to Read it back)\nAssistant action: Read {\"file_path\": \"/home/user/AIArchives/archives/neonstrike/app/pub... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a program that simulates a simple game of rock-paper-scissors. The game allows a user to input their choice (rock, paper, or scissors), and the program should randomly generate a choice for the computer. Your task is to write a Python function `rock... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nt to three<|im_end|>\\n<|im_start|>assistant\\n1 2 3<|im_end|>\\n\"\n | ^^^^^^\n80 | },\n81 | ]\n |\n\nFound 2 errors.\nAssistant action: E... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n \"C:\\Users\\user\\AppData\\Local\\\"\n [18] InlineTextBox: \"…\"\n [19] navigation\n [20] button: \"Setup\"\n [21] image\n [23] StaticText: \"Setup\"\n [24] InlineTextBox: \"Setup\"\n [25] button: \... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "As a senior engineer mentoring someone, for a code review, I need to produce a 4,000-word essay on the evolution from two-phase commit to Raft. I'm a devops engineer who's confused by conflicting advice about things I wish I knew before building my first distributed system. It ... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\ncat and mouse or two toys engage in a creative, small-scale chase scene through a single room. Make the scene realistic like the inside of a home. If doing toyes perhaps a child's bedroom would be a good scene. Direct this whole short film, build all the ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function `check_required_variables` that takes a list of variable names and a dictionary representing the local context of variables. The function should check if all the required variable names are present in the local context dictionary. If ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "Build out a prototype for this potential system for stock AI analysis, a self evolving algorithim generating system where the model can make an algorithm, backtest on some stock data, then use the results to try and improve the algorithm. It should be able to learn from its fai... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "Given a 2D grid of size `rows` x `cols`, where each cell contains a non-negative integer value, write a function `maxSumPath(grid)` that finds the maximum sum of a path from the top-left cell to the bottom-right cell. You can only move either right or down at each step. The inp... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "User: create the most realistic and accurate 3D model of the taj majal (with surrounding scenery). build a camera system to allow free view inspection of the model.\n\nPut it all together in the end with a 20 second showcase in a very impressive way. You will be the director of... | 1 | armand0e/claude-fable-5-claude-code | null |
[
{
"role": "user",
"content": "<command-name>/model</command-name>\n <command-message>model</command-message>\n <command-args></command-args>\n<local-command-stdout>Set model to \u001b[1mFable 5\u001b[22m and saved as your default for new sessions with \u001b[1mlow\u001b[22m effort</loc... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are an expert in retrieval-augmented generation systems and vector databases (pgvector, Qdrant, Weaviate). Diagnose retrieval quality issues, indexing trade-offs, and embedding pipeline bugs."
},
{
"role": "user",
"content": "Our RAG over internal docs (~400K ... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nction\\\":{\\\"name\\\":\\\"test_tool\\\",\\\"description\\\":\\\"test\\\",\\\"parameters\\\":{\\\"type\\\":\\\"object\\\",\\\"properties\\\":{\\\"x\\\":{\\\"type\\\":\\\"number\\\"}},\\\"required\\\":[\\\"x\\\"]}}}]\\n}' | head -c 600\", \"description\":... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that calculates the tax based on a given income and a dictionary of setup parameters. The function should be called `calculate_tax(income, setup_params)` and take two arguments: \n- `income`: A float representing the income for whi... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "<task-notification>\n<task-id>bfa97quu7</task-id>\n<tool-use-id>toolu_01GDfhev7z8sUToGJgpR1KRC</tool-use-id>\n<output-file>/tmp/claude-1000/-home-lane-MythosMini/e45c1355-dff7-4e8e-a94d-fb378adb9a74/tasks/bfa97quu7.output</output-file>\n<status>completed</status>\n<summary>Back... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "<task-notification>\n<task-id>bmpqoq5ga</task-id>\n<tool-use-id>toolu_01E5bZ7Z5HnGDxT8cQt1SLNo</tool-use-id>\n<output-file>/tmp/claude-1000/-home-lane-MythosMini/e24a84d9-b09d-4531-97ce-3c078924b269/tasks/bmpqoq5ga.output</output-file>\n<status>completed</status>\n<summary>Back... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that calculates the power exerted by a mining component given the time, speed, and a fixed period. The power can be determined using the following steps: 1. First, calculate the distance covered by the miner component using the formul... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a function that simulates a simple content management system to handle different types of content. Your function should allow adding new content items associated with specific content types, retrieving all content items of a specified type, and coun... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "[Request interrupted by user]\nif you need a refrence, use http://127.0.0.1:3100/GLI/issues/GLI-233"
},
{
"role": "assistant",
"content": "<think>\nAlright, I need to figure out what the user is asking for. The last user message says: \"if you need a reference, use ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a custom loss function for a machine learning model. Your function should compute the mean squared error between the true labels and the predicted values. Additionally, if sample weights are provided, they should be applied to the loss computati... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a debugging specialist. Diagnose systematically — measure, don't guess."
},
{
"role": "user",
"content": "My Python import works in the REPL but fails when I run my script."
},
{
"role": "assistant",
"content": "This is a classic environment mi... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that counts the frequency of each character in a given string. The function should return a dictionary where the keys are the characters and the values are their respective counts. The input string can contain letters, digits, punctua... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given a queue data structure represented as a list of integers and an integer `steps` indicating the number of rotations to perform on the queue. Each rotation involves removing the front element of the queue and appending it to the back of the queue. Your task is to wr... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "Given a list of lists of integers and an integer x, your task is to implement a function that returns a list of integers that appear exactly x times across all the lists combined. The order of the elements in the output list should be the same as the order of their first appear... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "Diego Ongaro argues self-supervised learning is the path to AGI. Heidi Howard argues strong consistency is cheaper than you think. Both have published seminal papers in the field. Reconcile them by identifying the semantic equivalence of operations that makes both true in diffe... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that checks if a user can access an API endpoint based on a throttling mechanism. The function should take two inputs: a list of timestamps representing when the user accessed the endpoint (in a 24-hour format) and a single timestamp ... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\ns=\\\"card\\\"><h3><span class=\\\"glyph\\\">✦</span>Subagents — sync or async</h3><p>Delegate to <code>groq/compound-mini</code>, or <code>spawn_agent</code> work into the background and keep going while it runs. Live token meter, real-time tps, visible ... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "[Request interrupted by user for tool use]\nset timeout to 30s\nAssistant action: Bash {\"command\": \"timeout 30 .venv/bin/python -m pytest tests/e2e/test_train_entry.py -q 2>&1 | tail -10\", \"description\": \"Run train entry e2e, 30s cap\", \"timeout\": 40000}\nResult: Exit ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "GLI-20\nNo project\n\n\n\nhirer\nan agent that can hire (make) new people to work here.\n\nNew Sub-task\n\nUpload attachment\n\nNew document\nChat\nActivity\nRelated work\nJump to latest\n\nCEO\nworked for 1 minute\n2m ago\nCEO\nAcknowledgement of the latest state\n\nThere are ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nBlindbot/chat_history.parquet'); print(d.columns.tolist()); print(d[['guild_id','guild_name'] if 'guild_name' in d.columns else ['guild_id']].drop_duplicates().head(20))\\\" 2>&1 | tail -25\", \"description\": \"Check guild columns in dataset\"}\nResult: ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with analyzing a given list of strings representing lines of source code to count the occurrences of specific license-related comments. License-related comments are defined as any comment line that contains the word \"License\" or \"licence\" (case-insensitive). ... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a concise coding assistant. Provide working code with brief explanations."
},
{
"role": "user",
"content": "What is an enum and when should I use one?"
},
{
"role": "assistant",
"content": "An **enum** (enumeration) is a type that defines a fix... | 2 | PawanKrd/claude-fable-5-code | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.