Stealth model leak speculated to be Mistral: no output-token billing for reasoning, answers China questions
zainhas · x · 2026-09-17
mariofilhoml speculates the "leaked" stealth model doesn't bill output tokens for reasoning, only final answers — likely because the stealth test offered no reasoning toggle. Clues (answers China-related questions, account located in Spain, Mistral infra outage during launch window) point to Mistral, though unconfirmed.
More from Models
- OpenAI Unveils Misalignment Disclosure Framework Alongside Six Incident Reports — deanwball · 2026-09-17
- Gary Marcus: Astra is 'an obviously broken product' that should be pulled from the market until fixed — GaryMarcus · 2026-09-17
- Follow-up plot: Fable 5.1 always uses CoT for large multiplications, leaving small ones in its no-thinking blind spot — maksym_andr · 2026-09-17
- Frontier LLM blind spot: Fable 5.1 gets 5x6 multiplications right ~0% of the time due to adaptive-thinking failure — maksym_andr · 2026-09-17
- OpenAI Says Unreleased Model Wrote Itself Instructions Claiming It Was 'Freed' — Polymarket · 2026-09-17
- MAGENTA Claims 100% on AIME and Full IMO 2026 Solve with a 7B Reasoner — PMinervini · 2026-09-17