Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Honnibal Challenges MIT's Astra Weight-Editing Claims

AI summary

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.

In-depth insight

The critique materially narrows the scope of a prominent result claiming that a model can inspect and edit another model's weights, separating small-network raw-weight experiments from an iterative, tool-assisted Qwen repair experiment.

MIT神作被锤:Astra爆改Qwen权重?就吹吧! – 量子位

< img id="wx_img" src="https://www.qbitai.com/wp-content/uploads/imgs/qbitai-logo-1.png" width="400" height="400">

MIT神作被锤:Astra爆改Qwen权重?就吹吧!

Jay 2026-11-05 15:10:56 来源:量子位

spaCy作者长文炮轰

#Astra#Qwen3.5-0.8B#Matthew Honnibal#MIT#spaCy#Explosion

Original · 5 min readRead the original
Group chat

No comments yet. Start the conversation.