royswastik (Swastik Roy)

published an article 2 months ago

Article

Part 6: Evaluating Agentic AI: Generalizability, Robustness, and the Benchmark Overfitting Problem

royswastik

•

Mar 12

published an article 2 months ago

Article

Part 5: Safety, Alignment, and Guardrails in Autonomous AI Agents

royswastik

•

Mar 12

published an article 2 months ago

Article

Part 4: Security Evaluation of Agentic AI Systems

royswastik

•

Mar 12

published an article 2 months ago

Article

Part 3: Observability and Interpretability in Agentic AI

royswastik

•

Mar 10

published an article 2 months ago

Article

Part 2: Evaluating Novelty and Scientific Discovery in AI Agents

royswastik

•

Mar 10

published an article 2 months ago

Article

Part 1: From Static Models to Autonomous Agents — The Evolving Landscape of AI Evaluation

royswastik

•

Mar 10

published an article about 1 year ago

Article

Shrinking Giants: The Quantization Mathematics Making LLMs Accessible

royswastik

•

May 3, 2025

• 2

published an article about 1 year ago

Article

Breaking Language into Tokens: How Transformers Process Information?

royswastik

•

May 3, 2025

• 2

published an article about 1 year ago

Article

Cross-Entropy Loss: Simple Explanations, Maths Explained

royswastik

•

May 3, 2025

• 4

published an article about 1 year ago

Article

Reinforcement Learning for Large Language Models: Beyond the Agent Paradigm

royswastik

•

Mar 19, 2025

• 8

published an article over 1 year ago

Article

Activation Steering: A New Frontier in AI Control—But Does It Scale?

royswastik

•

Feb 2, 2025

• 5

published an article over 1 year ago

Article

Is Attention Interpretable in Transformer-Based Large Language Models? Let’s Unpack the Hype

royswastik

•

Jan 28, 2025

• 4

Swastik Roy PRO

AI & ML interests

Organizations

Part 6: Evaluating Agentic AI: Generalizability, Robustness, and the Benchmark Overfitting Problem

Part 5: Safety, Alignment, and Guardrails in Autonomous AI Agents

Part 4: Security Evaluation of Agentic AI Systems

Part 3: Observability and Interpretability in Agentic AI

Part 2: Evaluating Novelty and Scientific Discovery in AI Agents

Part 1: From Static Models to Autonomous Agents — The Evolving Landscape of AI Evaluation

Shrinking Giants: The Quantization Mathematics Making LLMs Accessible

Breaking Language into Tokens: How Transformers Process Information?

Cross-Entropy Loss: Simple Explanations, Maths Explained

Reinforcement Learning for Large Language Models: Beyond the Agent Paradigm

Activation Steering: A New Frontier in AI Control—But Does It Scale?

Is Attention Interpretable in Transformer-Based Large Language Models? Let’s Unpack the Hype

Swastik Roy PRO

AI & ML interests

Organizations

royswastik's activity

Part 6: Evaluating Agentic AI: Generalizability, Robustness, and the Benchmark Overfitting Problem

Part 5: Safety, Alignment, and Guardrails in Autonomous AI Agents

Part 4: Security Evaluation of Agentic AI Systems

Part 3: Observability and Interpretability in Agentic AI

Part 2: Evaluating Novelty and Scientific Discovery in AI Agents

Part 1: From Static Models to Autonomous Agents — The Evolving Landscape of AI Evaluation

Shrinking Giants: The Quantization Mathematics Making LLMs Accessible

Breaking Language into Tokens: How Transformers Process Information?

Cross-Entropy Loss: Simple Explanations, Maths Explained

Reinforcement Learning for Large Language Models: Beyond the Agent Paradigm

Activation Steering: A New Frontier in AI Control—But Does It Scale?

Is Attention Interpretable in Transformer-Based Large Language Models? Let’s Unpack the Hype