Hacker Newsnew | past | comments | ask | show | jobs | submit | siva7's commentslogin

listen... i got agent skills.. im good at talking to agents!!

god thanks ClosedAI is still available

Orwellian speak for ... you won't get paid like our base engineers and when we want to get rid of you, we send you to our Siberian customer because you are a forward deployed engineer haha

Still i want to believe i'm wrong and it's a good job.


It's a well-paying job, but probably poison to your future career development, much as SRE or QA roles are, because you are now pigeonholed.

That's literally what they're looking for. To filter out ethical founders.

Ok, I'll never use max effort again on OAI models..

Is that... an x-rated, censored pelican?

Have been long time clauder but honestly codex feels much more liberating. Something you can't buy..

Software people are kind of different than doctors or lawyers.. probably also the reason why they act much more innovative than any other profession up to the point to invent the damn thing that replaces them (and likely wipes out humanity at some point if we believe the plot of terminator or matrix)

I swear some days ago someone here claimed Openai succeeded cutting down their compute cost by half with a breakthrough optimization. So this is it?

That was an article in The Information but it didn't read very well to me, I didn't get the impression the author was enough of a technical expert on how LLMs work to credibly evaluate the claim, which came from an insider rumor: https://www.theinformation.com/newsletters/ai-agenda/openai-...

> OpenAI engineers earlier this month told some colleagues they had figured out a way to more than halve the cost of inference, or running existing models, thanks to some newly-discovered optimizations, according to a person with knowledge of those discussions.


I bet that since this bug has made headlines, there are some panicked engineers at OpenAI desperately trying to figure out how to fix it without undoing their “magic optimisation”.

Is there any indication that optimization shipped? Depending on whether it’s R&D or pragmatic, I’d expect it to take months at least.

My understanding of the rumor is that it wasn't OpenAI itself, but one of the post-blip OpenAI breakaway groups (rumoured to be Thinking Machines) who have made a breakthrough and seem to be shopping it to OpenAI. I don't think it has actually been implemented by OpenAI yet.

I've switched 3 months ago to Codex because Claude got incredibly stupid. 6 months ago vice versa. It doesn't matter if you use Codex or Claude. Both will fuck with you at some point. Though Codex probably less.

At least OpenAI lets me use my own harness. Having to rely on insane PMs letting Claude Mythos go wild on the codebase has not been going well lately.

How do you mean OpenAI lets you use your own harness? I'm under the impression that a custom harness requires the OpenAI SDK, which requires api tokens rather than plus/pro accounts.

https://x.com/thsottiaux/status/2058071172361998482

"A little secret. About 5% of our production traffic is on the Pi harness, about another 5% is on OpenCode. Reminder you can use your ChatGPT account in a flourishing set of other tools.

We’ll continue to make Codex awesome, but you have options."


They will only do this while they have no users. Once they are compute constrained they won't let you do this anymore

That’s the beauty of using an open harness. I can jump ship if that ever happens.

Not just harnesses, you can even use the subscription in CI/CD. That, plus the fact that web chat does not count toward the same limits, is why I think the Codex personal plan is easily 10x the value of Claude Code.

https://developers.openai.com/codex/auth/ci-cd-auth


I'm never going back to claude from codex, including for the reasons you mentioned, but it must be said that web chat inference on ChatGPT is magic incantation, and I'm almost certain they're not serving the same models there as in Codex.

Claude web definitely feels like it's the same models behind as in API, with much less extra behavior/layers that make it behave differently.


How are you using it in ci/cd?

You must've missed the OpenAI's response to Anthropic forcing everyone to their own harness if they want subscription pricing: official endorsement of custom harnesses like opencode and pi even when used with Codex subscription.

I think they even partnered with opencode or something like that (don't remember).


Anthropic is the one that prohibits harnesses other than Claude Code on subscription plans and bans users for disobeying.

OpenAI officially allows that with subscriptions.


OpenAI doesn't require that; only Anthropic does.

OpenAI's harness is fully open source[1], and (AFAIK) doesn't come with any kind of signed-build request integrity verification like Claude does. And by that logic, if you're allowed to use their API with a fork of Codex that you yourself compiled, there's nothing stopping you from making some other harness act like such a fork.

[1] https://github.com/openai/codex


And although Codex Desktop is not open source (AFAIK), it does expose CDP and appserver which allowed me to build a Greasemonkey-like plugin system on top of it. It's surprisingly powerful, you can add transcript annotations, programmatically control the side panels, integrate a native-looking account switcher, and so on.

This sounds really cool. Do you have the source published anywhere?

Yup! MIT licensed, do whatever you want, you can also just use it directly with nodejs installed through `npx clankerbend` [0]. The screenshot on the github repo links you to a YouTube demo.

Warning: I use this daily myself for work, but beyond me arguing with it to get the CDP architecture, this was completely vibe-coded. I mostly use vim mode (jump to line, jump to prev/next user message) and the account switcher.

[0] https://github.com/onewillai/clankerbend


Will this problem not arise on other open source harness?

If you use GitHub Copilot you can switch between them in the same session if you want.

Yeah but now that you pay for tokens that's going to be bad for token caching.

Same with a third-party open harness.

I have no doubt any junior, no matter their background or degree, will break into tech fine like all of us did if they are in for the reasons we got in - being nerds and fascinated by software. You can't fake that.

Consider applying for YC's Fall 2026 batch! Applications are open till July 27.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: