Writing Weights Index test: open-source models struggle with weight-space programming task
khademinori · x · 2026-11-03
A retweet chain: @yoheinakajima marvels at how viral projects quickly spawn new ones, quoting @xingyudang's experiment — a Writing Weights Index derived from the recent Weight-Space Programming post, where open-source models struggled on the task.
More from Research
- Mechinterp's unsung root: nearly all weight-editing work traces back to one VGEL post — max_paperclips · 2026-11-03
- NVIDIA's AgentBaton cuts agent API costs 65.9% via well-timed model handoffs — amaarora · 2026-11-03
- SJTU-led paper proposes 'Avatar Intelligence' and an Agentic Oversight Index for personal agents — SJTU · 2026-11-03
- Vapor-cell atomic E-field sensor hits 0.2 mV/m/√Hz in 11 mm³, no electrodes — jwt0625 · 2026-11-03
- Anthropic Open-Sources FlashProve, Zero-Knowledge Proofs of AI Inference, Tested on Llama 4 Maverick — yenkel · 2026-11-03
- BiGym 2.0: Claude-written policies hit 51.9% on humanoid household tasks, nearing VLA — teortaxesTex · 2026-11-03