In the strongest example of "weight space programming", as the technique is called, Astra’s intervention raised Qwen3.5-0.8B’s MATH-500 score from 7.9% to 48.1% while touching approximately 0.016% of ...
MIT CSAIL researchers say GPT-6 Astra edited 0.016% of Qwen3.5-0.8B weights to fix reasoning loops, lifting MATH-500 from 7.9% to 48.1% without training.
Complete logs of the experiments in the blog post 'LLMs can understand and write neural network weights' - RikiyaT/lm_understand-logs ...
MIT has unveiled an innovative, groundbreaking paradigm dubbed "Weight Space Programming", representing a transformative new ...
India Today on MSN
They met at IIT Guwahati, built a brain-gaming app and raised USD 10 million in funding
Three IIT Guwahati graduates are giving mathematics a gaming twist through Matiks, a platform that combines mental ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results