Omar Khattab's lab now ships research as blog posts first — new batch coming
lateinteraction · x · 2026-11-03
Omar Khattab (lateinteraction) notes that almost all of his lab's research now goes out as blog posts first. His homepage shows several 2026 items published as blogs, including "Sparks of Weight-Space Programming" (LLMs natively reading & writing neural network weights), "Machine Studying", "Language model harnesses are compositional generalizers", "Pedagogical RL", and "OBLIQ-Bench" on retriever bottlenecks (NeurIPS 2026). He says a batch of releases he's been struggling to serialize is finally coming together.
More from Research
- New "private subquadratic" effort draws skepticism: just add weights to a Transformer — teortaxesTex · 2026-11-03
- GPT-6 Astra editing Qwen3.5 weights for 6x math gains? Skeptics call it cherry-picked demos — teortaxesTex · 2026-11-03
- OSVerify catches proof-killing errors that GPT-6-Pro and Codex both missed — james_y_zou · 2026-11-03
- Stanford and NUS hearables amplify hidden sound textures in real time at UIST 2026 — HanGuo97 · 2026-11-03
- Three LLM agents share one Godot escape room: logging what agents say vs. what they do — ViceGodIm · 2026-11-03
- Steering Qwen-Image-2.1 with Qwen3-VL's internal states, no training needed — zacharynado · 2026-11-03