HackerTrans
TopNewTrendsCommentsPastAskShowJobs

ccmcarey

no profile record

Submissions

Codex pricing to align with API token usage, instead of per-message

help.openai.com
211 points·by ccmcarey·3 mesi fa·193 comments

comments

ccmcarey
·3 mesi fa·discuss
No, ultrathink puts it in /effort high mode. There's no kw for one turn of effort max
ccmcarey
·3 mesi fa·discuss
Nope, they buried the lead a bit but this is coming for _all_ users, even pro/plus subscription plans. So you get chatgpt pro/plus benefits, and then effectively $20/$200 in credits for codex
ccmcarey
·4 mesi fa·discuss
AI slop comment
ccmcarey
·4 mesi fa·discuss
AI slop
ccmcarey
·7 mesi fa·discuss
I disagree, the claude models seem the best at tool calling, opus 4.5 seems the smartest, and claude code (+ claude model) seems to make good use of subagents and planning in a way that codex doesn't
ccmcarey
·6 anni fa·discuss
Looking at the language ref, you can specify the return types if you want to.
ccmcarey
·6 anni fa·discuss
Indeed, and how the answer to this problem always seems to be "use wlroots".

The wlroots github page[0] even says so: "about 50,000 lines of code you were going to write anyway".

Seems to me that if there's a necessary 50k LoC that every compositor needs, it should actually be a part of Wayland.

[0] https://github.com/swaywm/wlroots