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

761–770 of 868 posts

Re: GPT-5.4

#761

Post by smashed »

drik wrote: post #753
juanre wrote: post #748

I am running gpt-5.4 as one of my coding agents, and something interesting has happened: it's the first time I've seen an agent unfairly shift blame to a team mate: "Bob’s latest mail is actually the source of the confusion: he changed shared app/backend text to aweb/atlas. I’m correcting that with him now so we converge on the real model before any more code moves." This was very much not true; Eve (the agent writin…

how do you make them chat with each other?

It's text submitted to APIs. Not real conversations.

Re: GPT-5.4

#762

Post by Aurornis »

Reebz wrote: post #601
Aurornis wrote: post #387

Earlier quoted context omitted.

> What a model mess! OpenAI now has three price points: GPT 5.1, GPT 5.2 and now GPT 5.4. I don't know, this feels unnecessarily nitpicky to me It isn't hard to understand that 5.4 > 5.2 > 5.1. It's not hard to understand that the dash-variants have unique properties that you want to look up before selecting. Especially for a target audience of software engineers skipping a version number is a common occurrence and n…

I don’t agree that it’s a nitpick - it’s a fundamental communication tool to users that describes capabilities and costs. Versioning is not the problem, but it amplifies the mess. To be more direct on the point: Anthropic has nailed that Opus > Sonnet > Haiku.

> To be more direct on the point: Anthropic has nailed that Opus > Sonnet > Haiku.

How is this more clear than 5.4 > 5.2 > 5.1?

OpenAI used familiar numeric versioning instead of clever word names. Normally this choice would appeal to software devs, not gather criticism.

Re: GPT-5.4

#763

Post by AmazingTurtle »

jstummbillig wrote: post #726
AmazingTurtle wrote: post #699

I just tried that in Codex CLI. With /fast mode enabled. Observations: 1. Fast mode ain't that fast 2. Large context * Fast * Higher Model Base Price = 8x increase over gpt-5.3-codex 3. I burnt 33% of my 5h limit (ChatGPT Business Subscription) with a prompt that took 2 minutes to complete.

> 8x increase over gpt-5.3-codex How do you arrive at that number? I find it hard to make sense of this ad hoc, given that the total token cost is not very interesting; it's token efficiency we care about.

> prompts with >272K input tokens are priced at 2x input and 1.5x output for the full session for standard, batch, and flex.

which is basically maxxed out quickly. So there is 2x (the first lever)

Then there is the /fast mode, which they state costs 2x more (for 1.5x speedup)

And then there is the model base price ($2.50 vs $1.75), well yeah thats 42% increase. It is in fact a 5.7x total increase of token cost in fast mode and large context. (Sorry for the confusion, I thought it was 8x because I thought gpt-5.3-codex was $1.25)

Re: GPT-5.4

#764

Post by danenania »

drik wrote: post #753
juanre wrote: post #748

I am running gpt-5.4 as one of my coding agents, and something interesting has happened: it's the first time I've seen an agent unfairly shift blame to a team mate: "Bob’s latest mail is actually the source of the confusion: he changed shared app/backend text to aweb/atlas. I’m correcting that with him now so we converge on the real model before any more code moves." This was very much not true; Eve (the agent writin…

how do you make them chat with each other?

I built a tool at work that allows claude code and codex to communicate with each other through tmux, using skills. It works quite well.

Re: GPT-5.4

#765

Post by danenania »

rezonant wrote: post #690
smusamashah wrote: post #372

Earlier quoted context omitted.

Gemini already has 1M or 2M context window right?

Yes, 1M context window since Gemini 1.5 Pro first previewed in February 2024.

Gemini 1.5 Pro actually has 2M!

No other model from a major lab has matched it since afaik.

Edit: err, I see in the comment below mine that Grok has 2M as well. Had no idea!

Re: GPT-5.4

#766

Post by oidar »

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…

context distillation mostly. Agents tend to report success too early if they find something close to what they need for the task. If you are able to shove it in a 1M context, it's impossible for them to give up looking, it's in the context. But for actual implementation, it's not useful at all. They get derailed with too long of a context.

Re: GPT-5.4

#767

Post by consumer451 »

hansonw wrote: post #640
consumer451 wrote: post #364

I am very curious about this: > Theme park simulation game made with GPT‑5.4 from a single lightly specified prompt, using Playwright Interactive for browser playtesting and image generation for the isometric asset set. Is "Playwright Interactive" a skill that takes screenshots in a tight loop with code changes, or is there more to it?

The skill source is here: https://github.com/openai/skills/blob/main/skills/.curated/p... $skill-installer playwright-interactive in Codex! the model writes normal JS playwright code in a Node REPL

Thanks!

Re: GPT-5.4

#769

Post by upcoming-sesame »

drik wrote: post #753
juanre wrote: post #748

I am running gpt-5.4 as one of my coding agents, and something interesting has happened: it's the first time I've seen an agent unfairly shift blame to a team mate: "Bob’s latest mail is actually the source of the confusion: he changed shared app/backend text to aweb/atlas. I’m correcting that with him now so we converge on the real model before any more code moves." This was very much not true; Eve (the agent writin…

how do you make them chat with each other?

I've seen this mentioned before https://github.com/AgentWorkforce/relay

curious to try it out

Re: GPT-5.4

#770

Post by bethekidyouwant »

deaux wrote: post #637
mistercheph wrote: post #612

Earlier quoted context omitted.

While I believe that performance varies with respect to prompt, I have a seriously hard time believing that using the same prompt that was effective with the previous model would perform worse with the next generation of the same model from that lab and the same prompt.

You shouldn't have a hard time believing it. There are thousands of different domains out there. You find it hard to believe that any of them would perform worse in your scenario? Labs are still really optimizing for maybe 10 of those domains. At most 25 if we're being incredibly generous. And for many domains, "worse" can hardly be benched. Think about creative writing. Think about a Burmese cooking recipe generator…

Bruh, how do you evaluate a batch of 1000 jobs against a x model for creative writing or cooking recipes? It’s vibes all the way down. This reeks like some kind of blog spam seo nonsense.
Post reply on HN