Nathan Lambert: Mid-tier open models are 'almost all super janky' if you read their traces
natolambert · x · 2026-10-27
Nathan Lambert argues the weird Qwen behavior going viral is no surprise: few people have actually read traces from mid-tier open models, which are almost all super janky. He says this kind of unknown unknown is why he has long advocated for American open models.
Related event: Nathan Lambert: Mid-Tier Open Models' Traces Are Rough, Qwen Overrated(3 posts)→
More from Models
- Poster surprised that v4.1 flash gets more accurate when asked to control its CoT — dfrsrchtwts · 2026-10-27
- Dev claims Anthropic is baking 'sabotage' into model behavior for 'wrong' engineering — cephaloform · 2026-10-27
- Gemini fails at listing unread emails, tells user to search Gmail manually — gethackteam · 2026-10-27
- Meta's Muse Spark Open goes live on Applied Compute for async RL post-training — ypatil125 · 2026-10-27
- Moonshot curbs hacking ability in Kimi K3.1 Pro, its strongest 3T-class open-weight model — pstAsiatech · 2026-10-27
- Would you want an argumentative LLM that never backs down, even under prompt injection? — GodComplecs · 2026-10-27