GPT-5.2-Codex - Hackdot

Re:GPT-5.2-Codex by koakuma-chan on Thursday December 18, 2025 @01:37PM (#46316680)

I haven't used CC in a few months, what killer features have they added? I am using Cursor, it's clunky, but not that clunky so as to completely destroy model performance. I am pretty sure for my tasks (undocumented, buggy, legacy JavaScript project) GPT-5.2 is > all on any decent harness, because it doesn't give up or half-ass. It can run for 5 minutes or for 50 minutes, depending on your request.

[ Parent | on HN ]

Re:GPT-5.2-Codex by nunodonato on Thursday December 18, 2025 @03:05PM (#46317907)

we dont have capability to see the inner working of claude code, its not open source. You just use it and you see the difference. I've tried all of them, including anti-gravity. Nothing beats claude code

[ Parent | on HN ]

Re:GPT-5.2-Codex by HumanOstrich on Thursday December 18, 2025 @05:11PM (#46319513)

You can trace what's going back and forth over the wire between Claude Code and the model in use. That's going to be more insightful than their huge blob of JavaScript using React to render a terminal GUI.

[ Parent | on HN ]

Re:GPT-5.2-Codex by dkdcio on Thursday December 18, 2025 @02:00PM (#46316990)

lol bold claim initially for not using the primary competitor in months. I try to use all 3 (Claude Code, Codex CLI, Gemini CLI); there are tradeoffs between all 3

[ Parent | on HN ]

Re:GPT-5.2-Codex by koakuma-chan on Thursday December 18, 2025 @02:04PM (#46317036)

Read my reply to sibling comment. To my knowledge, Claude Code is at most marginally better than Cursor, and it's mostly the model that matters. Not saying there is no room for improvement on the tooling side, but no one seems to have come up with anything so far. Let me know which killer features Claude Code has, I would be happy to learn.

[ Parent | on HN ]

Re:GPT-5.2-Codex by dkdcio on Thursday December 18, 2025 @02:09PM (#46317106)

it’s the “agentic harness” — they have shipped tons of great features for the DevEx, but it’s the combination of better models (Sonnet 4.5 1M, now Opus 4.5) and the “prompting”/harness that improves how it actually performs

again I’m not saying Codex is worse, they’re just different and claiming the only one you actively use is the best is a stretch

edit: also FWIW, I initially dismissed Claude Code at launch, then loved Codex when it released. never really liked Cursor. now I primarily use Claude Code given I found Codex slow and less “reliable” in a sense, but I try to try all 3 and keep up with the changes (it is hard)

[ Parent | on HN ]

Re:GPT-5.2-Codex by koakuma-chan on Thursday December 18, 2025 @02:25PM (#46317294)

> they have shipped tons of great features for the DevEx

Such as?

> again I’m not saying Codex is worse, they’re just different and claiming the only one you actively use is the best is a stretch

I am testing all models in Cursor.

> I initially dismissed Claude Code at launch, then loved Codex when it released. never really liked Cursor

I also don't actually like Cursor. It's a VSCode fork, and a mediocre harness. I am only using it because my company refuses to buy anything else, because Cursor has all models, and it appears to them that it's not worth having anything else.

[ Parent | on HN ]

Re:GPT-5.2-Codex by dkdcio on Thursday December 18, 2025 @02:27PM (#46317340)

you conveniently ignored the most important part of my comment :)

> Such as?

changelog is here: https://github.com/anthropics/claude-code/blob/main/CHANGELO...

glhf

btw you started this thread with pure vibes, no evidence:

> I can confirm GPT 5.2 is better than Gemini and Claude. GPT 5.2 Codex is probably even better.

I’m saying you’re wrong. N=2, 1 against 1, one of us is making a much less bold claim

[ Parent | on HN ]

Re:GPT-5.2-Codex by koakuma-chan on Thursday December 18, 2025 @03:01PM (#46317846)

You do not seem to be able to tell me anything substantial, i.e. specifically how Claude Code is a better harness than Cursor.

> “prompting”/harness that improves how it actually performs

Is an abstract statement without any meaningful details.

[ Parent | on HN ]

Re:GPT-5.2-Codex by nunodonato on Thursday December 18, 2025 @01:42PM (#46316734)

it's not about features (although they've added plenty), its the internal tooling and the way the model is prompted.

[ Parent | on HN ]

Re:GPT-5.2-Codex by koakuma-chan on Thursday December 18, 2025 @01:46PM (#46316795)

The only thing I know that CC has that Cursor hasn't, is the ability to spawn agents. You can just prompt CC "spawn 10 agents" and it will make 10 subagents that run concurrently. But otherwise, I don't know what CC does that Cursor doesn't. On the contrary, AFAIK, CC doesn't index your codebase, and Cursor does.

[ Parent | on HN ]

Re:GPT-5.2-Codex by NoveltyEngine on Thursday December 18, 2025 @03:49PM (#46318501)

Surely CC has a lower price? How much do you have to pay Cursor for equivalent to what's provided in a 20x Claude Max plan?

[ Parent | on HN ]

Re:GPT-5.2-Codex by koakuma-chan on Thursday December 18, 2025 @04:52PM (#46319312)

I don't know. My company pays for it.

[ Parent | on HN ]

Re:GPT-5.2-Codex by mejutoco on Thursday December 18, 2025 @05:54PM (#46319964)

200$

https://cursor.com/pricing

[ Parent | on HN ]

Re:GPT-5.2-Codex by NoveltyEngine on Sunday December 21, 2025 @03:26PM (#46348085)

If I was paying API costs, I'd be spending about $1700/mo to get what I use on Claude's 20x plan. My understanding was that Cursor would give me about 1/4 of that, on their 20x plan.

[ Parent | on HN ]