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

641–650 of 868 posts

Re: GPT-5.4

#641

Post by kfse »

L-four wrote: post #370
strongpigeon wrote: post #344

Earlier quoted context omitted.

> Google essentially only has Preview models! The last GA is 2.5. As a developer, I can either use an outdated model or have zero insurances that the model doesn't get discontinued within weeks. What's funny is that there is this common meme at Google: you can either use the old, unmaintained tool that's used everywhere, or the new beta tools that doesn't quite do what you want. Not quite the same, but it did remind…

Gmail was in beta for 5 years, until 2009.

Until it had backup storage. Which ended up being useful in 2011 when tens of thousands of mailboxes were deleted due to a software bug and needed to be recovered from tape...

Re: GPT-5.4

#642

Post by motoboi »

Im planning a change that will save 20k a month of storage.

I absolutely could come up with the details and implementation by myself, but that would certainly take a lot of back and forth, probably a month or two.

I’m an api user of Claude code, burning through 2k a month. I just this evening planned the whole thing with its help and actually had to stop it from implementing it already. Will do that tomorrow. Probably in one hour or two, with better code than I could ever write alone myself.

Having that level of intelligence at that price is just bollocks. I’m running out of problems to solve. It’s been six months.

Re: GPT-5.4

#643

Post by smartbit »

beefsack wrote: post #628
bwat49 wrote: post #581

Earlier quoted context omitted.

yeah claude is great... but only if you pay $100-$200 a month

Many people buy two separate Claude pro subscriptions and that makes the limit become a non-issue. It works surprisingly well when you tend to hit the 5 hourly limit after a few hours, and hit the weekly limit after 4-5 days. $40 vs $100 is significant for a lot of people.

Thanks for the tip, didn’t think of using 2 subscriptions at the same company.

When reaching a limits, I switch to GLM 4.7 as part of a subscription GLM Coding Lite offered end 2025 $28/year. Also use it for compaction and the like to save tokens.

Re: GPT-5.4

#644

Post by applfanboysbgon »

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…

The real problem that OpenAI had was that their model naming was completely incomprehensible. 4.5, o3, 4o, 4.1 which is newer than 4.5. It was a complete clusterfuck. The blowback on that issue seems to have led them to misidentify the issue, but nobody was really asking for a single router model. Having a number of sequentially numbered and clearly labelled models is not actually a problem.

Re: GPT-5.4

#645

Post by nerdsniper »

bwat49 wrote: post #581
gizmodo59 wrote: post #538

Earlier quoted context omitted.

ChatGPT has given more for my 20$ than any other vendor. And that’s not even considering codex which is so good and the limits are much much higher

yeah claude is great... but only if you pay $100-$200 a month

To be honest it feels very worth my $200/mo. And I “only” make $80k/year. I used to have two ChatGPT subs but Claude is just so much better.

Re: GPT-5.4

#646

Post by keyle »

mattas wrote: post #5

"GPT‑5.4 interprets screenshots of a browser interface and interacts with UI elements through coordinate-based clicking to send emails and schedule a calendar event." They show an example of 5.4 clicking around in Gmail to send an email. I still think this is the wrong interface to be interacting with the internet. Why not use Gmail APIs? No need to do any screenshot interpretation or coordinate-based clicking.

The 'AI' endgame is a robot that sits in your seat and does all of your tasks.

Re: GPT-5.4

#647

Post by cheevly »

freedomben wrote: post #547

> When toggled on, /fast mode in Codex delivers up to 1.5x faster token velocity with GPT‑5.4. It’s the same model and the same intelligence, just faster. I hate these blog posts sometimes. Surely there's got to be some tradeoff. Or have we finally arrived at the world's first "free lunch"? Otherwise why not make /fast always active with no mention and no way to turn it off?

Try improving your attention to detail / reading skills.

Re: GPT-5.4

#648

Post by npn »

bethekidyouwant wrote: post #505
boringg wrote: post #481

Earlier quoted context omitted.

Like building on quicksand for dependencies. I guess though the argument is that the foundation gets stronger over time

What dependancy could possibly be tied to a non deterministic ai model? Just include the latest one at your price point.

the problem the price point is increasing sharply every time.

gemini 2 flash lite was $0.3 per 1Mtok output, gemini 2.5 flash lite is $0.4 per 1Mtok output, guess the pricing for gemini 3 flash lite now.

yes you guess it right, it is $1.5 per 1Mtok output. you can easily guest that because google did the same thing before: gemini 2 flash was $0.4, then 2.5 flash it jumps to $2.5.

and that is only the base price, in reality newer models are al thinking models, so it costs even more tokens for the sample task.

at some point it is stopped being viable to use gemini api for anything.

and they don't even keep the old models for long.

Re: GPT-5.4

#649

Post by weird-eye-issue »

abrookewood wrote: post #617
jbonatakis wrote: post #462

Earlier quoted context omitted.

Google is already sending notices that the 2.5 models will be deprecated soon while all the 3.x models are in preview. It really is wild and peak Google.

Public Service Announcement!! I don't know why the hell google do this, but when the deprecate a model, the error you will see is a Rate Limit error. This has caught me out before and it is super annoying.

Do you mean when they remove a model you get that error? Because deprecation means it will be removed in the future but you can still use it

Re: GPT-5.4

#650

Post by weird-eye-issue »

bethekidyouwant wrote: post #507
phainopepla2 wrote: post #415

Earlier quoted context omitted.

If you're trying to use LLMs in an enterprise context, you would understand. Switching models sometimes requires tweaking prompts. That can be a complete mess, when there are dozens or hundreds of prompts you have to test.

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

Tell us more about how you've never actually used these APIs in production
Post reply on HN