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

391–400 of 868 posts

Re: GPT-5.4

#391

Post by motoxpro »

arthurcolle wrote: post #337
__jl__ wrote: post #335

What a model mess! OpenAI now has three price points: GPT 5.1, GPT 5.2 and now GPT 5.4. There version numbers jump across different model lines with codex at 5.3, what they now call instant also at 5.3. Anthropic are really the only ones who managed to get this under control: Three models, priced at three different levels. New models are immediately available everywhere. Google essentially only has Preview models! Th…

There is a lot of opportunity here for the AI infrastructure layer on top of tier-1 model providers

This is what clouds like AWS, Azure, and GCP solve (vertex AI, etc). They are already an abstraction on top of the model makers with distribution built in.

I also don't believe there is any value in trying to aggregate consumers or businesses just to clean up model makers names/release schedule. Consumers just use the default, and businesses need clarity on the underlying change (e.g. why is it acting different? Oh google released 3.6)

Re: GPT-5.4

#392

Post by raincole »

__jl__ wrote: post #335

What a model mess! OpenAI now has three price points: GPT 5.1, GPT 5.2 and now GPT 5.4. There version numbers jump across different model lines with codex at 5.3, what they now call instant also at 5.3. Anthropic are really the only ones who managed to get this under control: Three models, priced at three different levels. New models are immediately available everywhere. Google essentially only has Preview models! Th…

They aggressively retire models, so GPT 5.1 and 5.2 are probably going to go soon.

Re: GPT-5.4

#393

Post by 361994752 »

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…

i guess you still have the "auto" as an option to route your request

Re: GPT-5.4

#394

Post by senko »

Just tested it with my version of the pelican test: a minimal RTS game implementation (zero-shot in codex cli): https://gist.github.com/senko/596a657b4c0bfd5c8d08f44e4e5347... (you'll have to download and open the file, sadly GitHub refuses to serve it with the correct content type)

This is on the edge of what the frontier models can do. For 5.4, the result is better than 5.3-Codex and Opus 4.6. (Edit: nowhere near the RPG game from their blog post, which was presumably much more specced out and used better engineering setup).

I also tested it with a non-trivial task I had to do on an existing legacy codebase, and it breezed through a task that Claude Code with Opus 4.6 was struggling with.

I don't know when Anthropic will fire back with their own update, but until then I'll spend a bit more time with Codex CLI and GPT 5.4.

Re: GPT-5.4

#395

Post by Aldipower »

So did they raised the ridiculous small "per tool call token limit" when working with MCP servers? This makes Chat useless... I do not care, but my users.

Re: GPT-5.4

#396

Post by jazzypants »

Aurornis wrote: post #388
Philip-J-Fry wrote: post #374

I find it quite funny how this blog post has a big "Ask ChatGPT" box at the bottom. So you might think you could ask a question about the contents of the blog post, so you type the text "summarise this blog post". And it opens a new chat window with the link to the blog post followed by "summarise this blog post". Only to be told "I can't access external URLs directly, but if you can paste the relevant text or descri…

Probably intentional. They don't want open, no-registration endpoints able to trigger the AI into hitting URLs.

But, why include the non-functional chat box in the article?

Re: GPT-5.4

#397

Post by judge2020 »

Philip-J-Fry wrote: post #374

I find it quite funny how this blog post has a big "Ask ChatGPT" box at the bottom. So you might think you could ask a question about the contents of the blog post, so you type the text "summarise this blog post". And it opens a new chat window with the link to the blog post followed by "summarise this blog post". Only to be told "I can't access external URLs directly, but if you can paste the relevant text or descri…

Works for me: https://rr.judge.sh/Labradorretriever/d6af05/chrome_j9rXJMlf...

Re: GPT-5.4

#398

Post by CryZe »

satvikpendem wrote: post #203
earth2mars wrote: post #180

Earlier quoted context omitted.

I am actually super impressed with Codex-5.3 extra high reasoning. Its a drop in replacement (infact better than Claude Opus 4.6. lately claude being super verbose going in circles in getting things resolved). I stopped using claude mostly and having a blast with Codex 5.3. looking forward to 5.4 in codex.

Same, it also helps that it's way cheaper than Opus in VSCode Copilot, where OpenAI models are counted as 1x requests while Opus is 3x, for similar performance (no doubt Microsoft is subsidizing OpenAI models due to their partnership).

I've been using both Opus 4.6 and Codex 5.3 in VSCode's Copilot and while Opus is indeed 3x and Codex is 1x, that doesn't seem to matter as Opus is willing to go work in the background for like an hour for 3 credits, whereas Codex asks you whether to continue every few lines of code it changes, quickly eating way more credits than Opus. In fact Opus in Copilot is probably underpriced, as it can definitely work for an hour with just those 12 cents of cost. Which I'm not sure you get anywhere else at such a low price.

Update: I don't know why I can't reply to your reply, so I'll just update this. I have tried many times to give it a big todo list and told it to do it all. But I've never gotten it to actually work on it all and instead after the first task is complete it always asks if it should move onto the next task. In fact, I always tell it not to ask me and yet it still does. So unless I need to do very specific prompt engineering, that does not seem to work for me.

Re: GPT-5.4

#399

Post by asabla »

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…

I really don't have any numbers to back this up. But it feels like the sweet spot is around ~500k context size. Anything larger then that, you usually have scoping issues, trying to do too much at the same time, or having having issues with the quality of what's in the context at all.

For me, I would say speed (not just time to first token, but a complete generation) is more important then going for a larger context size.

Re: GPT-5.4

#400

Post by observationist »

jazzypants wrote: post #396
Aurornis wrote: post #388

Earlier quoted context omitted.

Probably intentional. They don't want open, no-registration endpoints able to trigger the AI into hitting URLs.

But, why include the non-functional chat box in the article?

They're having service issues - ChatGPT on the web is broken for a lot of people. The app is working in android - I'd assume that the rollout hit a hitch and the chatbox in the article would normally work.
Post reply on HN