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…

Preview courtesy of The Decoder. The full article opens on their site.