Simon Willison·· 12 d ago
Qwen 3.8 27B on my laptop can interpret model weights, too
Qwen 3.8 27B on my laptop can interpret model weights, too
AI summary
Yesterday's hot paper was Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights by Rikiya Takehi, Jayden Teoh, Alex Zhang, and Omar Khattab.
Selection record
Threshold 76Media and individualsFirst 38Second 42
Not admittedSum of both 80 < twice the threshold 152
- Source tier
- Media and individuals; this tier's threshold is 76
- Pre-filter
- passed：实测本地LLM解读模型权重，属AI技术研究
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Simon Willison · simonwillison.net