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

GPT-5.4

openai.com

Post reply on HN
Print view View original

571–580 of 868 posts

Re: GPT-5.4

#571

Post by neom »

WXLCKNO wrote: post #551
damsta wrote: post #259

Earlier quoted context omitted.

There is extra cost for >272K: > For models with a 1.05M context window (GPT-5.4 and GPT-5.4 pro), prompts with >272K input tokens are priced at 2x input and 1.5x output for the full session for standard, batch, and flex. Taken from https://developers.openai.com/api/docs/models/gpt-5.4

Anthropic literally don't allow you to use the 1M context anymore on Sonnet and Opus 4.6 without it being billed as extra usage immediately. I had 4.5 1M before that so they definitely made it worse. OpenAI at least gives you the option of using your plan for it. Even if it uses it up more quickly.

Is that why it says rate limit all the time if you switch to a 1M model on Claude now? It kept giving me that so I switched to API account over the weekend for some vibe coding ran up a huuuuge API bill by mistake, whooops.

Re: GPT-5.4

#573

Post by wilg »

Alifatisk wrote: post #379

So let me get this straight, OpenAi previously had an issue with LOTS of different models snd versions being available. Then they solved this by introducing GPT-5 which was more like a router that put all these models under the hood so you only had to prompt to GPT-5, and it would route to the best suitable model. This worked great I assume and made the ui for the user comprehensible. But now, they are starting to in…

Well, they have older ones of course. But the current options actual users see is "Auto" or "Instant (5.3)" or "Thinking (5.4)". Not that complicated really.

Re: GPT-5.4

#574

Post by tymscar »

CactusBlue wrote: post #433
fhrow4484 wrote: post #360

Earlier quoted context omitted.

https://static0.anpoimages.com/wordpress/wp-content/uploads/...

Reminds of Unity features

I still remember the massive shift to SDRP and HDRP. Honestly, now in retrospect, almost a decade later, I think it was clearly done wrong. It was a mess, and switching over was a multi-week procedure for anything more than a hello world program, and what you got in return wasn’t something that looked better, just something that had the potential to.

Similar story with the whole networking stack. I haven’t used Unity in years now after it being my main work environment for years, but the sour taste it left in my mouth by moving everything that worked in the engine into plugins that barely worked will forever remain there.

Im sure its partly skill issue

Re: GPT-5.4

#575

Post by neom »

tedsanders wrote: post #59
minimaxir wrote: post #8

The marquee feature is obviously the 1M context window, compared to the ~200k other models support with maybe an extra cost for generations beyond >200k tokens. Per the pricing page, there is no additional cost for tokens beyond 200k: https://openai.com/api/pricing/ Also per pricing, GPT-5.4 ($2.50/M input, $15/M output) is much cheaper than Opus 4.6 ($5/M input, $25/M output) and Opus has a penalty for its beta >200…

Yeah, long context vs compaction is always an interesting tradeoff. More information isn't always better for LLMs, as each token adds distraction, cost, and latency. There's no single optimum for all use cases. For Codex, we're making 1M context experimentally available, but we're not making it the default experience for everyone, as from our testing we think that shorter context plus compaction works best for most p…

On Claude Code (sorry) the big context window is good for teams. On CC if you hit compact while a bunch of teams working it's a total shit show after.

Re: GPT-5.4

#576

Post by 0xbadcafebee »

gwd wrote: post #550
bethekidyouwant wrote: post #507

Earlier quoted context omitted.

This sounds made up. Much like “prompt engineering” Let’s hear an actual example

OK, so a while back I set up a workflow to do language tagging. There were 6-8 stages in the pipeline where it would go out to an LLM and come back. Each one has its own prompt that has to be tweaked to get it to give decent results. I was only doing it for a smallish batch (150 short conversations) and only for private use; but I definitely wouldn't switch models without doing another informal round of quality asses…

The big providers are gonna deprecate old models after a new one comes out. They can't make money off giant models sitting on GPUs that aren't taking constant batch jobs. If you wanna avoid re-tweaking, open weights are the way. Lots of companies host open weights, and they're dirt cheap. Tune your prompts on those, and if one provider stops supporting it, another will, or worst case you could run it yourself. Open weights are now consistently at SOTA-level at only a month or two behind the big providers. But if they're short, simple prompts, even older, smaller models work fine.

Re: GPT-5.4

#577

Post by slopinthebag »

solenoid0937 wrote: post #475
sampton wrote: post #416

Earlier quoted context omitted.

That's been my experience as well switching from Opus to Codex. Reasoning takes longer but answers are precise. Claude is sloppy in comparison.

Weird, I have had the opposite experience. Codex is good at doing precisely what I tell it to do, Opus suggests well thought out plans even if it needs to push back to do it.

This is just the stochastic nature of LLM's at play. I think all of the SOTA models are roughly equivalent, but without enough samples people end up reading into it too much.

Re: GPT-5.4

#578

Post by slopinthebag »

throwaway911282 wrote: post #440
sampton wrote: post #416

Earlier quoted context omitted.

That's been my experience as well switching from Opus to Codex. Reasoning takes longer but answers are precise. Claude is sloppy in comparison.

codex has been really good so far and the fast mode is cherry on top! and the very generous limits is another cherry on top

It's well worth the $20 to not deal with any limits and have it handle all the boilerplate repetitive BS us programmers seem forced to deal with. I think 80% of the benefit comes from spending that $20 (20%? :P) and just having it do the lame shit that we probably shouldn't have to do but somehow need to.

Re: GPT-5.4

#580

Post by vtail »

Marciplan wrote: post #489
vtail wrote: post #90

Earlier quoted context omitted.

My own experience is that I get far far more usage (and better quality code, too) from codex. I downgrade my Claude Max to Claude Pro (the $20 plan) and now using codex with Pro plan exclusively for everything.

Codex announced at 5.3 launch that until April all usage limits are upped so take that into account

that's a good point; hopefully they would just extend it automatically - but who knows...
Post reply on HN