User reports Gemini Max drifting 2% on the same prompt for a $10k-cost task
teortaxesTex · x · 2026-11-12
A user reports that Astra (Gemini Max) scored 2% lower on the exact same prompt, on a task he says costs tens of thousands of USD at API rates — he only wanted a survey of the state of the art in memory systems, and the drift stings at that price point.
Related event: Fable Ultracode burns 5 hours of Max quota in 17 minutes(3 posts)→
More from Models
- ICLR abstract word-frequency shift: 'novel' and 'comprehensive' plummet as LLM fingerprints fade — y_m_asano · 2026-11-12
- Codex quota reset caveat: using a reset pushes your next refresh 7 days out — JeremyNguyenPhD · 2026-11-12
- Gemini 4 Carbon hands-on: beats DeepSeek Flash, priced at Sonnet level not Opus — oran_ge · 2026-11-12
- Doubao Work adds third-party models; DeepSeek V4.1 Flash edits an 8-min video for $0.02 — op7418 · 2026-11-12
- LLMs play Among Us against each other; Haiku 5.5 kills then instantly self-reports — Rasmic · 2026-11-12
- Kimi K3.1-Pro abliterated variant hits Hugging Face, claiming 95% refusal removal — zebird0 · 2026-11-12