These things are so tricky because everyone has a seemingly conflicting experience. Part of the fun I guess!
Opus 4.7 + Rust is a killer combo.
I use Codex when Claude Code is down, and I only began using Claude when ChatGPT was down
yes codex is very fast, I go back to Claude for now
Heck I prefer DeepSeek to both of those.
I was running deepseek through claude's code agent harness. Maybe it works better through a different tool?
Harness also matters, and also provider. I was using openrouter and switched to the Deepseek api and suddenly all the tool call issues I was having resolved themselves. Flash is so damn fast at doing stuff like generating boilerplate I can’t go back to the bigger slower models.
My systems are hitting exponential delay retries, so this might not get better because retries overload things again.
> {'type': 'error', 'error': {'details': None, 'type': 'overloaded_error', 'message': 'Overloaded'}, 'request_id': 'req_ ...
I can see a weird spike in my cache hit-rate a few minutes before, so this might actually be some extra caching they have thrown in.