Matthew Honnibal
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 1
- Honnibal Challenges MIT's Astra Weight-Editing Claims
Matthew Honnibal argues that MIT's Astra research misleadingly groups small-network weight inspection with the repair of Qwen3.5-0.8B. According to Honnibal, the Qwen experiment used Python and up to 50 forward tests rather than directly reading raw weights, unlike the restricted small-network experiments. MIT claims Astra changed 0.016% of the model's weights and raised its math score from 7.9% to 48.1%, though Honnibal says the underlying tool-use progress remains significant.
量子位(原生 RSS) · 🔥 0
Experience and discussion from the community
Share my Matthew Honnibal experienceAsk about Matthew Honnibal
Nobody has shared their experience with Matthew Honnibal yet.