Hacker News new | ask | show | jobs
by stldev 31 days ago
I switched some time after Anthropic bricked their models with adaptive thinking. It's a legit mystery to me how people are still using CC professionally.

Codex is far less frustrating and manages context better. It's also costing me about 1/3rd as much as Opus 4.7 on CC.

1 comments

The only way to keep using CC for me has been to stick to 4.6 1M
Oh I didn't know you could type /model claude-opus-4-6 and still use it.

Thanks!

Yes, and /model claude-opus-4-6[1m] gets you the larger context window. Happy to help :)
Thanks for the hint, but is a large context window actually that useful? I tend to get garbage too often with a normal big context window.
IME, based on an in-house bench it's still good to about 20% on the 1M for 4.6 and 4.7 with a code base >50k loc. The trick I used before switching providers was to have it write a handoff when it hit ~18% of context and reset.

There are also many people running 4.5 with specific parameters that claim to be having luck.

The best way is to code in a way that doesnt break via model instruction nuances changing. 4.7 is superior