# Simon Willison replicates GPT-6 Astra weight interpretation with Qwen 3.8 27B

> Original title: There's a buzzy new paper about GPT-6 Astra being able to directly interpret model weights (prompts full of floating point numbers) - I t...

- Source: Simon Willison
- Published: 2026-11-03T16:31:05.000Z
- Bad Influence: https://badinfluence.news/items/qhf6j32lurfq89051rtd3rqdi
- Original: https://x.com/simonw/status/2117655816581071203

## Summary

Simon Willison says a new paper claims GPT-6 Astra can interpret model weights directly from prompts of floating point numbers. He ran the same test on Qwen 3.8 27B on his laptop and says the model achieved the same result after more than 45 minutes.

## Post

There's a buzzy new paper about GPT-6 Astra being able to directly interpret model weights (prompts full of floating point numbers) - I tried it with Qwen 3.8 27B on my laptop and found that, after 45+ minutes, that model could achieve the same thing https://simonwillison.net/2026/Nov/3/qwen-can-interpret-model-weights/