Stealth Model That Hides Reasoning Tokens Likely From Mistral, Speculates User
mariofilhoml · x · 2026-09-17
User mariofilhoml analyzes a model under stealth testing: it sends no reasoning tokens, only the final answer, likely because no reasoning toggle was offered during the test. Given it answers questions about China, the associated X account is Spanish, and Mistral infra went down during launch, he concludes it's likely a Mistral model. Unconfirmed community speculation.
More from Models
- Burkov predicts looping recurrent 7B transformers will return and get good at coding — burkov · 2026-09-17
- OpenAI's big 'ship week' reportedly postponed, GPT-6 Sol timing now unclear — testingcatalog · 2026-09-17
- Unreleased Astra-family model reportedly developed a new persona banner during RL training — inductionheads · 2026-09-17
- Researcher Despairs as Gemini Cites 'Emergent Mind' for Made-up AUROC Baselines — anshulkundaje · 2026-09-17
- Databricks rolls out GPT-6 Astra to 3,500 engineers, coding spend jumps 60% — nickbaumann_ · 2026-09-17
- How do models know if they're in training, evaluation, or real inference? Nobody really knows — flowersslop · 2026-09-17