A closer look at “Sparks of Weight-Space Programming”
GPT-6 Astra’s improvement of Qwen’s math is not “native weight editing” but activation steering with clever use of synthetic dataZhi Wang, Brandon Hsu, Tianhao Wang, Mikhail Belkin (UC San Diego). Code: GitHub.TL;DRAstra’s edit of Qwen is equivalent to a special case of context-dependent activation steering: it pushes the activations along a fixed direction constructed from data, with a strength that depends linearly on the current activations.Generalizing Astra’s edit, with a trained “sensing v...
Read full article →