Model safety checks now reset chats and wipe 30 minutes of work
MarcJSchmidt · x · 2026-07-24
The poster says a model workflow now triggers additional safety checks even for “just math things,” and that choosing “Retry with a faster model” switched them to a lower tier, wiped 30 minutes of work, cleared all messages, and reset the conversation to the root prompt.
The screenshot shows a console warning that the request needs extra safety checks and offers three options: retry with a faster model, keep waiting, or learn more.
More from Models
- Microsoft says MAI models are now routing traffic in Copilot, Excel, and Outlook — satyanadella · 2026-07-24
- A user says OpenAI is in a different league on usefulness than Opus 4.8 — FlorianGallwitz · 2026-07-24
- OpenAI and Anthropic logos frame a “the labs never sleep” snapshot of frontier rivalry — MeetPatelTech · 2026-07-24
- GPT-5.6 Benchmarked on Slay the Spire, Shows Surprising Gaming Prowess — Jsevillamol · 2026-07-24
- Laguna S-2.1 GGUF fixes its chat template and thinking traces — fragment_me · 2026-07-24
- Grok 4.5 lands on iOS, Android, web, and X with stronger coding and context handling — mark_k · 2026-07-24