GPT-6 Astra edited Qwen’s weights and raised MATH-500 from 7.9% to 48.1% in author-run tests. How weight-space programming works—and its limits.
Can an LLM write a neural network that IS a benefits formula, exactly? Weight-space programming experiments on SNAP, EITC, SSI, and Medicaid arithmetic. - ctrimm/weight-space-programming ...
Tsinghua's HarnessPro cuts AI coding agent costs 26% while boosting accuracy without model retraining. Factory Droid 1.0 ...
A new MIT CSAIL blog post is making the rounds in AI circles this week, and it describes something that sounds almost ...
Disruption rarely arrives from the direction an industry expects, and oftentimes, outside of the industry entirely.
Astra identifies game policies from raw weight matrices and fixes reasoning loops in Qwen3.5-0.8B by editing 0.016% of parameters, lifting MATH-500 scores from 7.9% to 48.1% without training loops.
Foundry in the real world: Turning LLM hunches into verified findings – Security Loop Series, Part 2
See how Foundry turns LLM hunches into verified findings on Langflow, MLflow, and PyGoat, using an evidence gate and an honest look at token cost.
Key Takeaways AI is moving beyond chat interfaces. Developers now build systems that use tools, retain context and take actions […] ...
MIT CSAIL shows GPT-6 Astra reading and editing neural weights as text, fixing Qwen3.5-0.8B math from 7.9% to 48.1% by changing 0.016% of weights. Every morning the day's AI news, new AI startups and ...
Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results