ai training4 min read
GPT-6 Astra sees the matrix and reprograms other AI models directly through their weights
MIT researchers show that OpenAI's GPT-6 Astra can read and deliberately rewrite the weights of other AI models without traditional training. In one experiment, Astra boosted a Qwen model's math accuracy from 7.9 to 48.1 percent by changing just 0.016 percent of its weights.
By Maximilian SchreinerThe Decoder

Read the full story
Originally published by The Decoder on Nov 4, 2026.
Comments
Sign in to join the discussion.