Simon Willison Replicates Model Weight Reading with Qwen
After a paper claimed GPT-6 Astra can directly interpret model weights, Simon Willison replicated the feat in 45 minutes with Qwen 3.8 27B on his laptop, marking a new advance in interpretability.
2026-11-04 ~ 2026-11-04 · 2 related posts
- Episode 1: MIT Study: Frontier LLM Edits Weights Directly to Boost Small Model Math Scores Sixfold(2026-11-03, 100 posts)
- Episode 2: LLMs Editing Model Weights: From Survey to Self-Editing Experiments(2026-11-03, 5 posts)
- Episode 3: Editing 0.016% of weights fixes Qwen reasoning loops, lifting MATH-500 to 48.1%(2026-11-03, 2 posts)
- Episode 4: Model eval audit continues: claimed gains hold but MATH-500 anomaly persists(2026-11-03, 3 posts)
- Episode 5: MIT weight-space programming independently replicated, with 20x gains on newest models(2026-11-03, 7 posts)
- Episode 6: Weight-Editing LLMs Raise Fear of Recursive Self-Improvement(2026-11-03, 3 posts)
- Episode 7: "GPT-6 Edits Weights for 6x Gains" Debunked as Thinking-Mode Ablation(2026-11-03, 2 posts)
- Episode 8: Viral Claim That Astra Can Read and Write Qwen Weights Debunked by Experts(2026-11-03, 3 posts)
- Episode 9: Simon Willison Replicates Model Weight Reading with Qwen(2026-11-04, 2 posts)
- Simon Willison replicates GPT-6 Astra weight-interpretation feat with Qwen 3.8 27B in 45 minutes — cephaloform · 2026-11-04
- Qwen 3.8 27B can also interpret model weights, Simon Willison reports — tarruda · 2026-11-04