'Like gene editing for neural networks': MIT researchers used GPT-6 Astra to edit Qwen's open weights directly, boosting math performance

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 ...
GitHub

SKILL.md

AI/LLM security offensive checklist: prompt injection, jailbreaking, model extraction, training data poisoning, adversarial inputs, LLM-assisted attack automation, and AI system reconnaissance. Use ...
eu.36kr

MIT allowed GPT-6 Astra to directly modify Qwen's weights, and its math scores have soared.

MIT has unveiled an innovative, groundbreaking paradigm dubbed "Weight Space Programming", representing a transformative new ...
GitHub

README.md

Paper: Skill-based Model-based Reinforcement Learning, especially Section 3.3, equations 2–5. This is an educational adaptation of offline joint pretraining, not a complete SkiMo reproduction. You ...

Recursion Reports Third Quarter 2026 Financial Results and Extends Cash Runway; Highlights Positive Clinical Data in REC-4881 and REC-1245, Sanofi Development Candidate Option ...

New Phase 2 REC-4881 data presented at CGA-IGC in an expanded adult population aged 18 years and older show deep, durable polyp burden ...
kingy.ai

Weight-Space Programming: How GPT-6 Astra Raised Qwen’s MATH-500 Score Sixfold

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.