Data science, career and other topics
20 April 2026
FIPO - an RL algorithm that fixes one of the core limitations of RL for LLM reasoning - credit assignment. Instead of giving every token in a rollout the same outcome advantage, it re-weights tokens by a discounted future-KL signal, enabling longer and more effective reasoning chains.
09 April 2026
A review of Keith Bourne second edition of Unlocking Data with Generative AI and RAG, covering the running example that ties all 20 chapters together, explanations of agentic RAG, and where the book is most useful in practice.
06 April 2026
A review of Sandip Kulkarni book on RLHF, covering its strengths as a structured learning resource, its reliance on both older an newer models, and who will benefit most from reading it.
23 March 2026
A practical walkthrough of redesigning a Jekyll personal website — adding search, dark mode, structured data, and a full card-based redesign using Claude Code. What changed, what broke, and what it is like to iterate on a site with an AI coding assistant.
16 March 2026
HACRL proposes a new paradigm for reinforcement learning - instead of training models in isolation, multiple agents collaborate by sharing successful trajectories during training. This simple idea enables more efficient exploration and improves performance across heterogeneous models.
23 February 2026
A review of DroPE, a simple but counterintuitive method that extends LLM context length by dropping positional embeddings at inference and achieves strong zero-shot long-context generalization without retraining.
Type at least 2 characters to search...