Srush tempers hype: the new model is just a base model, post-training not finished yet
srush_nlp · x · 2026-10-16
AI researcher Sasha Rush offers a key reality check on a newly discussed model release: what's out now is only the base model, post-training isn't done yet. He adds that the team's previous model was arguably just a proof of concept, so current results shouldn't be judged as a finished product.
Related event: Sasha Rush: Hyped New Model Is Just a Base Model, Post-Training Incomplete(2 posts)→
More from Models
- Five rounds of adversarial prompting make Opus 5.5 and Argon converge on identical output — LanceCharger · 2026-10-16
- DIY benchmark ranks 18 models on subjective judgments, GLM-5.3 tops consensus match — arkuto · 2026-10-16
- Bindu Reddy: Google's Argon excels at complex doc writing at half the cost of Opus — bindureddy · 2026-10-16
- MAI-2 is 2x bigger than V4-Pro while V4.1F is 3x smaller: Microsoft's scaling ladder questioned — teortaxesTex · 2026-10-16
- Step 5 Preview hits DeepInfra day-zero: 600B MoE, 1M context, $1/M input tokens — StepFun_ai · 2026-10-16
- Liquid AI's d1-ultra Decision Model Hits OpenRouter at $0.042/M Input Tokens — JosephJacks_ · 2026-10-16