they dont change the model weights (no frontier lab does). if you have evals and all prompts, tool calls the same, I'm curious how you are saying performance decreased..

you should include anthropic's deal with palantir.. they are the first to actually do it.

thank you, let me take a look into this

so much hatred

what a thoughtful comment! HN is so low quality these days

you get more more from codex than claude any day. and its more reliable as well.

https://xcancel.com/OpenAI/status/2029620619743219811 you can see comparisons here

like the claude models via anthropic?

codex has been really good so far and the fast mode is cherry on top! and the very generous limits is another cherry on top

It's well worth the $20 to not deal with any limits and have it handle all the boilerplate repetitive BS us programmers seem forced to deal with. I think 80% of the benefit comes from spending that $20 (20%? :P) and just having it do the lame shit that we probably shouldn't have to do but somehow need to.

I know. I feel troubled for all providers. (I have never used Grok, for example, for obvious ethical reasons.) But Anthropic seems, currently, better than OpenAI. I always want to encourage the better behaviour and discourage the worst.

my m4max runs fan at high speed! just have few electron apps open..