Re:Getting AI to work in complex codebases
by CuriouslyC on Tuesday September 23, 2025 @08:23PM
(#45354623)
Yes, the $200 tier. I do use GPT5/Gemini 2.5 to generate plans that I hand off to codex, that's actually how I keep my agents super busy.
Re:Getting AI to work in complex codebases
by wahnfrieden on Tuesday September 23, 2025 @08:46PM
(#45354811)
Bracing myself for the inevitability of keeping 3-5 Pro subscriptions at once
Re:Getting AI to work in complex codebases
by CuriouslyC on Tuesday September 23, 2025 @09:32PM
(#45355178)
I thought about it, but I don't think it's necessary. Grok-4-fast is actually quite a good model, you can just set up a routing proxy in front of codex and route easy queries to it, and for maybe $50/mo you'll probably never hit your GPT plan quota.
Re:Getting AI to work in complex codebases
by wahnfrieden on Tuesday September 23, 2025 @09:46PM
(#45355298)
Maybe, but I'd rather pay for consistent access to state of the art quality even if it's slower (which hasn't mattered much while parallelizing)
Btw one thing that helps conserve context/tokens is to use GPT 5 Pro to read entire files (it will read more than Codex will, though Codex is good at digging) and generate plans for Codex to execute. Tools like RepoPrompt help with this (though it also looks pretty complicated)