| ▲ | pcuaron a day ago | ||||||||||||||||
Excellent, so Gemini 3.7 can trash your codebase even faster (but seriously: don't trust this model) | |||||||||||||||||
| ▲ | drusepth a day ago | parent | next [-] | ||||||||||||||||
What should you be looking out for as bad behavior from this model? I've daily-driven 3.5, 3.6, and now 3.7 for however long it's been out (alongside Opus, as I hit daily limits on both subs each day) and haven't noticed anything "untrustworthy". | |||||||||||||||||
| |||||||||||||||||
| ▲ | seanmcdirmid a day ago | parent | prev [-] | ||||||||||||||||
Are 3.5, 3.6 any better? It is pretty flaky, Deepseek v4 flash is more reliable than 3.7 flash at least. | |||||||||||||||||