Three Gemini Flash releases in six weeks: models ship faster than evals can finish
ColbyHawker · x · 2026-09-03
Google's Gemini Flash line shipped 3.6, 3.7, and 3.8 within six weeks. The author quips that new models now arrive before you can finish an eval, underscoring how frontier iteration has outpaced evaluation workflows.
Related event: Gemini Flash ships 3.6-3.8 in six weeks, testers complain of churn(2 posts)→
More from Models
- Mocked benchmark shows DeepSeek's document chart grounding badly misaligned — burkov · 2026-10-18
- Dev complains Claude's habit of saying "not done" is his biggest pain point — jasonkneen · 2026-10-18
- Open-weight TYGER speech decision model makes 80ms turn-taking calls for full-duplex voice agents — solyarisoftware · 2026-10-18
- Paying Google AI subscriber blocked: custom-domain Workspace accounts can't access AI Studio — ChrisRackauckas · 2026-10-18
- Running Ling 3.1 Flash (560B MoE, 25B Active) Across 4 DGX Sparks via llama.cpp RPC — BerryBlush_Rogers691 · 2026-10-18
- Users press OpenAI on long-delayed Adult Mode a year after it was promised — ___Patrice___ · 2026-10-18