Live data from Hacker News

GPT-5.3-Codex

openai.com

501–510 of 634 posts

Re: GPT-5.3-Codex

#501
post #479

Earlier quoted context omitted.

Why even come to this site if you're so anti-innovation? Today with LLMs you can literally spend 5 minutes defining what you want to get, press send, go grab a coffee and come back to a working POC of something, in literally any programming language. This is literally stuff of wonders and magic that redefines how we interface with computers and code. And the only thing you can think of is to ask if it can do somethin…

Agree but you are talking about a POC, and he is talking about reliable, working software. this phase of LLM are perfect for POCs and there you can have 10x speedup, no question. But going from a POC to a working reliable software is where most of our time is spent anyway even without LLMS. With LLMs this phase becomes worse. we speedup 10x the poc time, we slow down almost as much in the next phases, because now you…

At our company we use AI extensively to see if we missed edge cases and it does a pretty good job in pointing us towards places which could be handled better.

I know we all think we are always so deep into absolutely novel territory, which only our beautiful mind can solve. But for the vast majority of work done in the world, that work is transformative. You take X + Y and you get Z. Even with brand new api, you can just slap in the documentation and navigate it in order of magnitude faster than without.

I started using it for embedded systems doing something which I could literally find nothing about in rust but plenty in arduino/C code. The LLM allowed me to make that process so much faster.

Re: GPT-5.3-Codex

#502
post #478

Earlier quoted context omitted.

There are different kinds of innovation. I want AI that cures cancer and solves climate change. Instead we got AI that lets you plagiarize GPL code, does your homework for you, and roleplay your antisocial horny waifu fantasies.

Hard problems take more time than easy problems

Of course, but at least DeepMind is taking a crack at the important problems

Re: GPT-5.3-Codex

#503

Earlier quoted context omitted.

5.2 Codex became my default coding model. It “feels” smarter than Opus 4.5. I use 5.2 Codex for the entire task, then ask Opus 4.5 at the end to double check the work. It's nice to have another frontier model's opinion and ask it to spot any potential issues. Looking forward to trying 5.3.

Opus 4.5 is more creative and better at making UIs

Unless it's scroll bar theming then my God it's bad. it told me it gives up. Gemini 3 got stuck but the right prompt it did work.

Re: GPT-5.3-Codex

#504
post #347

Earlier quoted context omitted.

Codex now lets you tell the LLM tgings in the middle of its thinking without interrupting it, so you can read the thinking traces and tell it to change course if it's going off track.

That just seems like a UI difference. I've always interrupted claude code added a comment and it's continued without much issue. Otherwise if you just type the message is queued for next. There's no real reason to prefer one over the other except it sounds like codex can't queue messages?

Codex can queue messages, but the queue only gets flushed once the agent is done with whatever it was working on, whereas Claude will read messages and adjust accordingly in the middle of whatever it is doing. It sounds like OP is saying that Codex can now do this latter bit as well.

Re: GPT-5.3-Codex

#505

I think Anthropic rushed out the release before 10am this morning to avoid having to put in comparisons to GPT-5.3-codex! The new Opus 4.6 scores 65.4 on Terminal-Bench 2.0, up from 64.7 from GPT-5.2-codex. GPT-5.3-codex scores 77.3.

I do not trust the AI benchmarks much, they often do not line up with my experience. That said ... I do think Codex 5.2 was the best coding model for more complex tasks, albeit quite slow. So very much looking forward to trying out 5.3.

Codex 5.3 seems to be a lot chattier. As in, it comments in the chat about things it has done or is about to do. They don't show up as "thinking" CoT blocks, but as regular outputs, but overall the experience is somewhat more like Claude is in that you can spot the problems in model's reasoning much earlier if you keep an eye on it as it works, and steer it away.

Re: GPT-5.3-Codex

#506
post #404

Earlier quoted context omitted.

> Model costs continue to collapse And yet RAM prices are still sky high. Game consoles are getting more expensive, not cheaper, as a result. When will competition benefit those consumers? Or consumers of desktop RAM?

The free market has simply decided these consumers are not as relevant as the others.

Maybe the free market is wrong.

Re: GPT-5.3-Codex

#507
post #144

Earlier quoted context omitted.

In my personal experience the GPT models have always been significantly better than the Claude models for agentic coding, I’m baffled why people think Claude has the edge on programming.

GPT 5.2 codex plans well but fucks off a lot, goes in circles (more than opus 4.5) and really just lacks the breadth of integrated knowledge that makes opus feel so powerful. Opus is the first model I can trust to just do things, and do them right, at least small things. For larger/more complex things I have to keep either model on extremely short leashes. But the difference is enough that I canceled my GPT Pro sub s…

I'd say that GPT 5.2 did slightly better on the stuff that I'm working on currently compared to Opus 4.5, but it's rather niche - a fancy Lojban parser in Haskell). However Opus is much easier to steer interactively because you can see what it's doing in more detail (although 5.3 is much improved in that regard!). I wouldn't feel empty-handed with either model, and both wrote large chunks of code for this project.

All that said, the single biggest reason why I use Codex a lot more is because the $200 plan for it is so much more generous. With Claude, I very quickly burn through the quota and then have to wait for several days or else buy more credit. With Codex, running in High reasoning mode as standard with occasional use of XHigh to write specs or debug gnarly issues, and having agents run almost around the clock in the background, I have hit the limit exactly once so far.

Re: GPT-5.3-Codex

#508

Earlier quoted context omitted.

In my experience, OpenAI gives you unreasonable amounts of compute for €20/month. I am subscribed to both and Claude's limits are so tiny compared to ChatGPT's that it often feels like a rip-off. Claude also doesn't let you use a worse model after you reach your usage limits, which is a bit hard to swallow when you're paying for the service.

If their pay as you go api token prices reflect their internal costs then it makes sense, but it could also be that claude makes money while gpt sells at loss to stay on top. Claude is way more expensive overall, and way more limited with flat rate subscriptions opus: 5/25 gpt: 1.75/14

Given how much you can use Codex on their $200 plan, I'm virtually certain that it's subsidized.

As to why, I think in part it is because people who are willing to pay that much per month are much more likely to be using it heavily on "serious" tasks, which is, of course, a goldmine for training data - even if you can't use the inputs directly for training, just looking at various real world issues and how agents handle them (or not) is valuable, especially when all the low-hanging fruit have already been picked.

I wouldn't even be surprised if the $20 users are actually subsidizing the $200 users.

Re: GPT-5.3-Codex

#509
post #99

The behind the scenes on deciding when to release these models has got to be pretty insanely stressful if they're coming out within 30 minutes-ish of each other.

It’s also functionally not likely without some sort of insider knowledge or coordination

The AI labs tell their partners when the models are coming out, the partners might be sharing the news with their sources in other AI labs.

Re: GPT-5.3-Codex

#510
post #68

Earlier quoted context omitted.

Its kind of a suck up that more or less confirms the beef stories that were floating around this past week. In case you missed it. For example: Nvidia's $100 billion OpenAI deal has seemingly vanished - Ars Technica https://arstechnica.com/information-technology/2026/02/five-... Specifically this paragraph is what I find hilarious. > According to the report, the issue became apparent in OpenAI’s Codex, an AI code-gen…

> OpenAI staff reportedly attributed some of Codex’s performance limitations to Nvidia’s GPU-based hardware. They should design their own hardware, then. Somehow the other companies seem to be able to produce fast-enough models.

> They should design their own hardware

They made a deal with Cerebras for fast inference.

Post reply on HN