HiGHS
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 1
- A linear program reproduces Astra’s weight edit
Nathan Barry’s analysis of MIT CSAIL’s “Sparks of Weight-Space Programming” reports that GPT-6 Astra inferred a trained game and generated weights for a small network that outperformed networks trained with PPO, without gradients or a training loop. He also reports that editing 0.016% of Qwen3.5-0.8B’s weights raised MATH-500 accuracy from 7.9% to 48.1% and IFEval from 21.0% to 62.3%. Barry argues that Astra’s roughly eight-hour search for the loop-removal edit can be expressed as a linear program. He reports that a couple of LP solves produced the same effect with one-eighth as many changed weights, while his custom PDHG GPU solver reached within 0.2% of the optimum in about a minute.
Hacker News 首页(100+ 分) · 🔥 0
Experience and discussion from the community
Share my HiGHS experienceAsk about HiGHS
Nobody has shared their experience with HiGHS yet.