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

OpenAI o3 and o4-mini

openai.com

Post reply on HN
Print view View original

461–470 of 527 posts

Re: OpenAI o3 and o4-mini

#461

Post by danpalmer »

erikw wrote: post #213

Interesting... I asked o3 for help writing a flake so I could install the latest Webstorm on NixOS (since the one in the package repo is several months old), and it looks like it actually spun up a NixOS VM, downloaded the Webstorm package, wrote the Flake, calculated the SHA hash that NixOS needs, and wrote a test suite. The test suite indicates that it even did GUI testing- not sure whether that is a hallucination…

Are you sure about all of this? You acknowledged it might be a hallucination, but you seem to mostly believe it? o3 doesn't have the ability to spin up a VM.

https://xcancel.com/TransluceAI/status/1912552046269771985 / https://news.ycombinator.com/item?id=43713502 is a discussion of these hallucinations.

As for the hash, could it have simply found a listing for the package with hashes provided and used that hash?

Re: OpenAI o3 and o4-mini

#464

Post by momoelz »

I find o4 very bad at coding. I tried to improve a script created by 3.5 mini-high with o4 mini-high and it doesn't return nearly as good results as what i used to get by o3.5

Re: OpenAI o3 and o4-mini

#465

Post by FergusArgyll »

brokencode wrote: post #64
ApolloFortyNine wrote: post #39

Maybe OpenAI needs an easy mode for all these people saying 5 choices of models (and that's only if you pay) is simply too confusing for them. They even provide a description in the UI of each before you select it, and it defaults to a model for you. If you just want an answer of what you should use and can't be bothered to research them, just use o3(4)-mini and call it a day.

I personally like being able to choose because I understand the tradeoffs and want to choose the best one for what I’m asking. So I hope this doesn’t go away. But I agree that they probably need some kind of basic mode to make things easier for the average person. The basic mode should decide automatically what model to use and hide this from the user.

I thought sama said that that's the plan for gpt-5: a router which'll choose the right model and thinking level for you

Re: OpenAI o3 and o4-mini

#466

Post by steinvakt2 »

littlestymaar wrote: post #193
Sol- wrote: post #182

Interesting that using tools to zoom around the image is useful for the model. I was kind of assuming that these models were beyond such things and could attend to all aspects image simultaneously anyway, but perhaps their input is still limited in the resolution? Very cool, in any case, spooky progress as always.

There's just a certain amount of things the image encoder can process at once. It's pretty apparent when you give the models a big table in an image.

But isn't this basically what the conv layer does...?

Re: OpenAI o3 and o4-mini

#467

Post by thom »

hatefulmoron wrote: post #415
thom wrote: post #397

Earlier quoted context omitted.

Mad tangent, but as an old timey MtG player it’s always jarring when someone uses “the meta” not to refer to the particular dynamics of their competitive ecosystem but to a single strategy within it. Impoverishes the concept, I feel, even in this case where I don’t actually think a single model is best at everything.

I'm a World of Warcraft & Dota 2 player, using "the meta" in that way is pretty common in gaming these days I think. The "meta" is still the 'metagame' in the competitive ecosystem sense, but it also refers to strategies that are considered flavor of the month (FOTM) or just generally safe bets. So there's "the meta", and there's "that strategy is meta", or "that strategy is the meta."

Yeah, I accept that "Nash equilibrium" isn't likely to catch on at this stage.

Re: OpenAI o3 and o4-mini

#468

Post by bool3max »

erikw wrote: post #213

Interesting... I asked o3 for help writing a flake so I could install the latest Webstorm on NixOS (since the one in the package repo is several months old), and it looks like it actually spun up a NixOS VM, downloaded the Webstorm package, wrote the Flake, calculated the SHA hash that NixOS needs, and wrote a test suite. The test suite indicates that it even did GUI testing- not sure whether that is a hallucination…

I find that so incredibly unlikely. Granted I haven't been keeping up to date with the latest LLM developments - but has there even been any actual confirmation from OpenAI that these models have the ability to do such things in the background?

Re: OpenAI o3 and o4-mini

#469

Post by yMEyUyNE1 »

M4v3R wrote: post #298

Ok, I’m a bit underwhelmed. I’ve asked it a fairly technical question, about a very niche topic (Final Fantasy VII reverse engineering): https://chatgpt.com/share/68001766-92c8-8004-908f-fb185b7549... With right knowledge and web searches one can answer this question in a matter of minutes at most. The model fumbled around modding forums and other sites and did manage to find some good information but then started to…

> Not to lie me in the face.

Are you saying that, it deliberately lied to you?

> With right knowledge and web searches one can answer this question in a matter of minutes at most.

Reminded me of Dunning Kruger curve, the ai model at the first peak and you at the latter.

Re: OpenAI o3 and o4-mini

#470

Post by Carbonhell »

rsanheim wrote: post #179

`ETOOMANYMODELS` Is there a reputable, non-blogspam site that offers a 'cheat sheet' of sorts for what models to use, in particular for development? Not just openAI, but across the main cloud offerings and feasible local models? I know there are the benchmarks, and directories like huggingface, and you can get a 'feel' for things by scanning threads here or other forums. I'm thinking more of something that provides u…

I have been using this site: https://artificialanalysis.ai/ . It's still about benchmarks, and it doesn't do deep dives into specific use cases, but it's helpful to compare models for intelligence vs cost vs latency and other characteristics.
Post reply on HN