> These results show sparks of Weight-Space Programming, which may extend beyond what we’d expect from humans or conventional algorithms. This might be a big deal for both optimization and interpretability. […]
> Likewise, asked to make Qwen3.5-0.8B better at math without gradients, Astra identifies an issue in its weights causing reasoning loops that Qwen’s own model card warns about, and fixes this by natively editing 0.016% of the weights.
How is that not misleading when the in the Qwen case “natively editing” refers to a mere directional ablation, a well-known technique that has been used a ton by both academics and hobbyists over the past few years?
alt Hacker News
> These results show sparks of Weight-Space Programming, which may extend beyond what we’d expect from humans or conventional algorithms. This might be a big deal for both optimization and interpretability. […]
> Likewise, asked to make Qwen3.5-0.8B better at math without gradients, Astra identifies an issue in its weights causing reasoning loops that Qwen’s own model card warns about, and fixes this by natively editing 0.016% of the weights.
How is that not misleading when the in the Qwen case “natively editing” refers to a mere directional ablation, a well-known technique that has been used a ton by both academics and hobbyists over the past few years?