Article
Swastik Roy PRO
royswastik
AI & ML interests
None yet
Recent Activity
published an
article
5 days ago
Part 5: Safety, Alignment, and Guardrails in Autonomous AI Agents published an
article
5 days ago
Part 4: Security Evaluation of Agentic AI Systems Organizations
None yet
published an
article 5 days ago
published an
article 5 days ago
Article
Part 5: Safety, Alignment, and Guardrails in Autonomous AI Agents
published an
article 5 days ago
Article
Part 4: Security Evaluation of Agentic AI Systems
published an
article 7 days ago
Article
Part 3: Observability and Interpretability in Agentic AI
published an
article 7 days ago
Article
Part 2: Evaluating Novelty and Scientific Discovery in AI Agents
published an
article 7 days ago
Article
Part 1: From Static Models to Autonomous Agents — The Evolving Landscape of AI Evaluation
published an
article 11 months ago
Article
Shrinking Giants: The Quantization Mathematics Making LLMs Accessible
•
2
published an
article 11 months ago
Article
Breaking Language into Tokens: How Transformers Process Information?
published an
article 11 months ago
Article
Cross-Entropy Loss: Simple Explanations, Maths Explained
•
3
published an
article 12 months ago
Article
Reinforcement Learning for Large Language Models: Beyond the Agent Paradigm
•
8
published an
article about 1 year ago
Article
Activation Steering: A New Frontier in AI Control—But Does It Scale?
•
5
published an
article about 1 year ago
Article
Is Attention Interpretable in Transformer-Based Large Language Models? Let’s Unpack the Hype
•
4