Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

A week of using Codex more than Claude

allaboutcoding.ghinda.com

Post reply on HN
Print view View original

211–220 of 311 posts

Re: A week of using Codex more than Claude

#211

Post by inquirerGeneral »

qurren wrote: post #197
217 wrote: post #10

while everyone is somehow still stuck on and fascinated by claude, heres your quick update on the sota of coding models and harnesses mid august 2026 codex is good, both cli and desktop app, you get lots of usage on any plan. sol is good! and gets the job done, write or dictate a very long and thoughtful prompt, and leave sol xhigh or max fast working on it for an hour or so omp is an amazing harness, any feature cla…

Any opinions (by anyone really) on how much I can trust Claude vs. Codex (vs. something else) to not leak my coding conversations or use them for training? I have the appropriate privacy settings set up but wondering how much I can trust each company with them.

[dead]

Re: A week of using Codex more than Claude

#212

Post by inquirerGeneral »

alasdair_ wrote: post #131
trjordan wrote: post #31

Earlier quoted context omitted.

Not mentioning Grok 4.6 here is a crime. Fast and accurate. And it can communicate, unlike the gobbledygook that comes out of Claude.

Elon burned too many bridges to warrant ever supporting anything he is associated with ever again.

[dead]

Re: A week of using Codex more than Claude

#213

Post by drivebyhooting »

sharlos201068 wrote: post #205
drivebyhooting wrote: post #187

Earlier quoted context omitted.

Because ULA and the senate launch system is better?

SpaceX's valuation is as an AI company that happens to launch rockets on the side.

You can’t justify AI company valuations either.

Only one of those capabilities can actually deliver kinetic solutions. Meanwhile big tech revenue is delivering ad solutions.

Re: A week of using Codex more than Claude

#214

Post by piotraleksander »

felipeerias wrote: post #133

I use Claude Code with a MCP that lets it communicate with Codex and tell it to “iterate until both of you are happy”. The agents then go for several rounds criticising each other plans and implementations, catching big and small issues on each other’s work. The end result is not perfect, but it is a lot better than what I can get from relying on only one model.

btw, there's a dedicated plugin for similar setup https://github.com/openai/codex-plugin-cc

Re: A week of using Codex more than Claude

#215

Post by sdthjbvuiiijbb »

timr wrote: post #182
sdthjbvuiiijbb wrote: post #180

Earlier quoted context omitted.

Bizarre reply. It's not "dominating everything you do". It's one specific thing. Grok exists in a very crowded space and it's incredibly easy to not use it. If this is your reaction to someone taking a very easy stand on their personal principles, it does not reflect well on you.

"Bizarre" only in the sense that you're purposely trying not to understand. Literally every commodity product is in a crowded space, and easily substituted. If it's a good product (Grok Build objectively is one of the very best in the space), it's a good product, and it's self-defeating to avoid it because you hate a guy for political reasons. Just as it would be nonsensical to avoid shopping at WalMart, Target, or a…

On the contrary, I'm trying to understand as best I can. I find your position so completely devoid of any inkling of personal or social responsibility that it takes quite some empathy to muster up a reply that's not wildly uncivil.

I also think it's callous to brush away "political reasons" as though it's some trivial abstract thing. Or perhaps it comes from a place of nihilism?

I choose not to give my money to people I think are enormously evil. That's really all there is to it. I don't see why this is "nonsensical".

Re: A week of using Codex more than Claude

#216

Post by joddystreet »

I have completely moved away from Claude to Codex. OpenAI models are better at following instructions and skill use.

Claude generates more code, tries to build things that are not planned or needed, repeats same mistakes over and over.

Chatgpt on the other hand just does enough, within a project would not repeat the same mistakes, tries to guess your workflow, so you don’t have to ask it to run the same.

If you need more control over your code/projects, if you know what you want to get done, use Codex.

If you have no idea what you’re doing and are happy to let LLM drive the thing, use Claude.

Codex/Chagpt is for the competent.

Re: A week of using Codex more than Claude

#217

Post by smartbit »

zatkin wrote: post #208
artdigital wrote: post #137

Earlier quoted context omitted.

I do the same with Gemini. I have a skill that teaches any AI to use the antigravity cli (agy) to communicate with Gemini and ask to review or check decisions

There's some real research-backed evidence that this approach elevates output quality, and it was even discussed a few months back: https://news.ycombinator.com/item?id=47169627

Anthropic confirmed it in their recent report https://news.ycombinator.com/item?id=49316271

> We expect that agents coordinating in the wild will act in higher variance ways than we see here, because they’ll have different backgrounds and therefore different contexts. They also, presumably, won’t all be Claudes.

Re: A week of using Codex more than Claude

#218

Post by solarkraft »

217 wrote: post #10

while everyone is somehow still stuck on and fascinated by claude, heres your quick update on the sota of coding models and harnesses mid august 2026 codex is good, both cli and desktop app, you get lots of usage on any plan. sol is good! and gets the job done, write or dictate a very long and thoughtful prompt, and leave sol xhigh or max fast working on it for an hour or so omp is an amazing harness, any feature cla…

> gemini 3.7 is great for speed

Does this mean it can break your code faster now, or have they actually worked on making it good? Every single time I've given Gemini a chance (in older point versions) it would almost immediately break something and throw itself into a loop. I have not experienced it being useful for programming and almost never heard an account of somebody else doing so.

Remember those stories of LLMs catastrophically deleting entire repositories or databases? It was always Gemini.

I'm amazed that you'd trust Gemini over DeepSeek, which I've had very good experiences with after some tuning, though still on a relatively short leash.

Re: A week of using Codex more than Claude

#219

Post by vrosas »

solarkraft wrote: post #218
217 wrote: post #10

while everyone is somehow still stuck on and fascinated by claude, heres your quick update on the sota of coding models and harnesses mid august 2026 codex is good, both cli and desktop app, you get lots of usage on any plan. sol is good! and gets the job done, write or dictate a very long and thoughtful prompt, and leave sol xhigh or max fast working on it for an hour or so omp is an amazing harness, any feature cla…

> gemini 3.7 is great for speed Does this mean it can break your code faster now, or have they actually worked on making it good? Every single time I've given Gemini a chance (in older point versions) it would almost immediately break something and throw itself into a loop. I have not experienced it being useful for programming and almost never heard an account of somebody else doing so. Remember those stories of LLM…

3.6+ have been fine for me. They still introduce bugs but at least they don’t make you wait an hour for them like Claude does.

Re: A week of using Codex more than Claude

#220

Post by timr »

sdthjbvuiiijbb wrote: post #215
timr wrote: post #182

Earlier quoted context omitted.

"Bizarre" only in the sense that you're purposely trying not to understand. Literally every commodity product is in a crowded space, and easily substituted. If it's a good product (Grok Build objectively is one of the very best in the space), it's a good product, and it's self-defeating to avoid it because you hate a guy for political reasons. Just as it would be nonsensical to avoid shopping at WalMart, Target, or a…

On the contrary, I'm trying to understand as best I can. I find your position so completely devoid of any inkling of personal or social responsibility that it takes quite some empathy to muster up a reply that's not wildly uncivil. I also think it's callous to brush away "political reasons" as though it's some trivial abstract thing. Or perhaps it comes from a place of nihilism? I choose not to give my money to peopl…

> I find your position so completely devoid of any inkling of personal or social responsibility that it takes quite some empathy to muster up a reply that's not wildly uncivil.

Oh stop. Other people believe different things than you. If you cannot see how using a coding agent is not "devoid of personal or social responsibility", then you really need to step away from the keyboard.

Post reply on HN