GPT-6 Astra sees the matrix and reprograms other AI models directly through their weights

Summary

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. The approach could fundamentally simplify AI optimization but still hits clear limits. The article GPT-6 Astra sees the matrix and reprograms other AI models directly through their weights appeared first on The Decoder .

Lotu Radar provides attributed news summaries and links to the original publisher. Full reporting and copyright remain with the source.