# Two Minute Papers — 'OpenAI's Astra Just Opened The Black Box Of AI'

> Two Minute Papers explains how GPT-6 Astra reads a network's weights and rewrites them directly.

- Org: Two Minute Papers
- Date: 2026-11-07
- Category: video
- Source: https://www.youtube.com/watch?v=GJ6PMUm5oTA
- Canonical page: https://ai-tldr.dev/releases/two-minute-papers-astra-black-box-nov7/

## In short

Two Minute Papers covers Weight-Space Programming, the MIT CSAIL study where GPT-6 Astra reads raw neural network weights and edits them by hand, with no training loop.

## What it is

'OpenAI's Astra Just Opened The Black Box Of AI' went up on the Two Minute Papers channel on 7 November 2026. The video's description points to the Weight-Space Programming blog post by MIT CSAIL researchers, which tests whether GPT-6 Astra can work out what a network computes just by looking at its weights.

## How it works

In the study, Astra gets the weights as text or as tensors in a sandbox where it cannot run the network, plus a small budget of forward passes. In one experiment it found a direction behind Qwen3.5-0.8B's looping on math problems and subtracted it, lifting MATH-500 from 7.9% to 48.1% by changing 0.016% of the weights.

## Why it matters

Reading and repairing a model without data or gradient training would be a new tool for interpretability. The video gives a short visual walk-through of a result that has drawn both excitement and pushback this week.

## Who it's for

anyone curious about interpretability research

## Links

- [Watch on YouTube](https://www.youtube.com/watch?v=GJ6PMUm5oTA)
- [Weight-Space Post](https://rikiyat.github.io/blog/weight-space-programming/)
- [Experiment Logs](https://github.com/RikiyaT/lm_understand-logs)