Omar Khattab

Even advanced LLMs struggle to replicate human researchers' ability to find inspiring prior work, highlighting a significant gap in AI's scientific intuition.

Users can now interactively critique and optimize their AI-driven data queries, transforming opaque analytics into a transparent, controllable process.

LLMs trained with Vector Policy Optimization (VPO) learn to produce diverse solutions that unlock previously unsolvable problems in evolutionary search, outperforming models optimized for single scalar rewards.

LLM performance hinges on the code around the model, and Meta-Harness proves that automating the design of this "harness" can significantly boost results across diverse tasks.