We found and fixed two issues that could explain this degradation of the capability of GPT-5.5 in Codex over the last ~ 48 hours.
We are monitoring over the coming hours to fully confirm and I will reset usage limits this evening.
Apologies and now is the time for /fast maxxing.
Don't just reset Codex rate limits for fun, it costs money.
Don't just reset Codex rate limits for fun, it costs money.
... but the vibes are good ...
I have reset Codex rate limits for ALL paid plans to celebrate a good week and allow everyone to build more with GPT-5.5. Enjoy
was messing with the OpenAI base URL in Cursor and caught this
accounts/anysphere/models/kimi-k2p5-rl-0317-s515-fast
so composer 2 is just Kimi K2.5 with RL
at least rename the model ID
The gap is closing. China is catching up.
Kimi-K2 Thinking crushes GPT-5 and Claude 4.5 Sonnet in several benchmarks, while costing 6 times less compared to Sonnet
It's the best open-source model period
Its core focus is on agentic tasks and software development. It can now execute 200–300 sequential tool calls
Moonshot applied Quantization-Aware Training to support native INT4 of Kimi-K2 Thinking
K2 Thinking is now even better at writing. It responds more personally and emotionally