Recent content on James Kirk
When AI competes against a powerful chess engine, it seems doomed - unless the AI learns how to cheat. I have been reading Yoav Goldberg’s gist about multi-LLM-agent systems , Eric Ma’s “What makes an agent?” , Dynomight’s posts about LLMs playing chess and DeepMind’s paper Mastering Board Games by External and Internal Planning with Language Models . These…
It probably feels liberating to be a little bit wrong, all of the time. Computers are, fundamentally, excellent calculators. Nearly every bit of value creation by computing since the dawn of the computing age is traceable to this fact. The information revolution was built on the ability to calculate faster, more comprehensively, and more reliably. Our most fundamental understanding of a computer…
James Kirk Machine Learning, Recommender Systems, Information Retrieval, AI GitHub LinkedIn Bluesky Twitter Instagram