GPT-6 edits Qwen3.5-0.8B weights directly: 0.016% of params changed, math up 6x
khademinori · x · 2026-11-03
Rikiya Takehi's team asked GPT-6 Astra to directly edit Qwen3.5-0.8B weights to improve math. The model changed only 0.016% of weights — no gradients, no training — fixing the 0.8B model's reasoning loops, improving math up to 6x and instruction following 3x.
They call this "Weight-Space Programming": frontier LLMs can natively read and write neural network weights. A follow-up notes the total cost of the work was on the order of $1,000, similar to the original RLM blog a year ago. Full write-up in the linked blog post.
More from Models
- Fabricated citations collapse from 55% to 0%: new models nearly fix the hallucinated-reference failure — RexDouglass · 2026-11-03
- Apple hints at monetizing third-party AI apps for new revenue on earnings call — TechCrunch AI · 2026-11-03
- Writing Weights Index: Open-Source Models Struggle at Weight-Space Programming — eliebakouch · 2026-11-03
- Gemini 4 Argon ships, putting Google back in the frontier model race after a year-long lull — danshipper · 2026-11-03
- Hands-on audit punctures Astra's '0.016% weight programming' claim: it just disabled Qwen's thinking mode — teortaxesTex · 2026-11-03
- Leak: Unreleased astra6.2 builds a 3DS-style Mario Kart in 20 min under 1% quota — lxfater · 2026-11-03