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

481–490 of 527 posts

Re: OpenAI o3 and o4-mini

#481

Post by hansmayer »

motorest wrote: post #454
SkyPuncher wrote: post #419

Earlier quoted context omitted.

There's a bit of a skill to it. Good architecture plans help. Telling it where in an existing code base it can find things to pattern match against is also fantastic. I'll often end up with a task that looks something like this: * Implement Foo with a relation to FooBar. * Foo should have X, Y, Z features * We have an existing pattern for Fidget in BigFidget. Look at that for implementation * Make sure you account fo…

> Good architecture plans help. This is they key answer right here. LLMs are great at interpolating and extrapolating based on context. Interpolating is far less error-prone. The problem with interpolating is that you need to start with accurate points so that interpolating between them leads to expected and relatively accurate estimates. What we are seeing is the result of developers being oblivious to higher-level…

Yes, with a bit of work around prompting and focusing on closed context, or as you put it, interpolating, you can get further. But the problems is that, this is not how the LLMs were sold. If you blame someone for trying to use it by specifying fairly high level prompts - well isn´t that exactly how this technology was being advertised the whole time? The problem is not the bad workman, the problem is that the tool is not doing what it is advertised as doing.

Re: OpenAI o3 and o4-mini

#482

Post by petesergeant »

TuxSH wrote: post #185
petesergeant wrote: post #157

Earlier quoted context omitted.

> Why is there an o3-mini and an o4-mini? Why on earth are there so many models? Because if they removed access to o3-mini — which I have tested, costed, and built around — I would be very angry. I will probably switch to o4-mini when the time is right.

They just did that, at least for chat

It seems clear to me I would have built an app around the API, not the chat window.

Re: OpenAI o3 and o4-mini

#483

Post by ben_w »

throwuxiytayq wrote: post #147
ben_w wrote: post #46

4o and o4 at the same time. Excellent work on the product naming, whoever did that.

Just wait until they announce oA and A0. They jokingly admitted that they’re bad at naming in the 4.1 reveal video, so they’re certainly aware of the problem. They’re probably hoping to make the model lineup clearer after some of the older models get retired, but the current mess was certainly entirely foreseeable.

Energy Intensive Exceptional Intelligence (Omni-domain), AKA E-I-E-I-O.

Re: OpenAI o3 and o4-mini

#484

Post by unsupp0rted »

erikw wrote: post #218
unsupp0rted wrote: post #85

Earlier quoted context omitted.

Main advantage over Sonnet is Gemini 2.5 doesn't try to make a bunch of unrelated changes like it's rewriting my project from scratch.

What language / framework are you using? I ask because in a Node / Typescript / React project I experience the opposite- Claude 3.7 usually solves my query on the first try, and seems to understand the project's context, ie the file structure, packages, coding guidelines, tests, etc, while Gemini 2.5 seems to install packages willy-nilly, duplicate existing tests, create duplicate components, etc.

Node / Vue

Re: OpenAI o3 and o4-mini

#485

Post by kupopuffs »

scarface_74 wrote: post #234
kupopuffs wrote: post #229

Earlier quoted context omitted.

what kind of employees does Docusign employ? surely Digital Documents dont require physical onsite distribution centers and labor

Just look at their careers page

Its a lot of sales/account managers. and some engineers

wow the sales go hard in this product

Re: OpenAI o3 and o4-mini

#486

Post by greenavocado »

rashkov wrote: post #439
greenavocado wrote: post #422

Earlier quoted context omitted.

Recommend using RAG for this. Make the Haskell or OCaml documentation your knowledge base and index it for RAG. Then it makes a heck of a lot more sense!

How does one do that? As far as I can tell neither Claude or chatgpt web clients support this. Is there a third party tool that people are using?

They can't

You can use openwebui with deepseek v3 0324 via API with for example deepinfra as provider for your embeddings and text generation models

Re: OpenAI o3 and o4-mini

#487

Post by throwanem »

Hackbraten wrote: post #452
throwanem wrote: post #371

Earlier quoted context omitted.

I feel perhaps I've been unkind to many people in my thoughts, but I'm conflicted. I don't understand myself to be particularly fearless, but what times call more for courage than times like these? How do people afraid even to try to practice courage expect to find it, when there isn't time for practice any more?

You have only so many spoons available per crisis. Even picking your battle can become a problem. I've been out in the streets, protesting and raising awareness of climate change. I no longer do. It's a pointless waste of time. Today, the climate change deniers are in charge.

I don't assume I'm going to be given the luxury of picking my battles, and - though I've been aware of "spoon theory" since I watched it getting invented at Shakesville back in the day - I've never held to it all that strongly, even as I acknowledge I've also never been quite the same since a nasty bout of wild-type covid in early 2020. Now as before, I do what needs doing as best I can, then count the cost. Some day that will surely prove too high, and my forward planning efforts will be put to the test. Till then I'm happy not to borrow trouble.

I've lived in this neighborhood a long time, and there are a couple of old folks' homes a block or so from here. Both have excellent views, on one frontage each, of an extremely historic cemetery, which I have always found a wonderfully piquant example of my adopted hometown's occasionally wire-brush sense of humor. But I bring it up to mention that the old folks don't seem to have much concern for spoons other than to eat with, and they are protesting the present situation regularly and at considerable volume, and every time I pass about my errands I make a point of raising a fist and hollering "hell yeah!" just like most of the people who drive past honk in support.

Will you tell them it's pointless?

Re: OpenAI o3 and o4-mini

#488

Post by stogot »

Workaccount2 wrote: post #75
zapnuk wrote: post #20

Surprisingly, they didn't provide a comparison to Sonnet 3.7 or Gemini Pro 2.5—probably because, while both are impressive, they're only slightly better by comparison. Lets see what the pricing looks like.

Looks like they are taking a page from Apple's book, which is to never even acknowledge other products exist outside your ecosystem.

Apple has commercials for a decade making fun of “PCs”

Re: OpenAI o3 and o4-mini

#489

Post by namaria »

spaceywilly wrote: post #200
leesec wrote: post #87

Earlier quoted context omitted.

"haven't actually done much" being popularizing the chat llm and absolutely dwarfing the competition in paid usage

They have 500M weekly users now. I would say that counts as doing something.

While bleeding cash faster than anything else in History.

Re: OpenAI o3 and o4-mini

#490

Post by motorest »

saberience wrote: post #477
motorest wrote: post #456

Earlier quoted context omitted.

> That said, 100% pure vibe coding is, as far as I can tell, still very much BS. I don't really agree. There's certainly a showboating factor, not to mention there is currently a goldrush to tap this movement to capitalize from it. However, I personally managed to create a fully functioning web app from scratch with Copilot+vs code using a mix of GPT4 and o1-mini. I'm talking about both backend and frontend, with bas…

People were making a front and backend web app in half a day using Ruby on Rails way before LLMs were ever a thing, and their code quality was still much better than yours! So vibe coding, sure you can create some shitty thing which WORKS, but once it becomes bigger than a small shitty thing, it becomes harder and harder to work with because the code is so terrible when you're pure vibe coding.

> People were making a front and backend web app in half a day using Ruby on Rails way before LLMs were ever a thing, and their code quality was still much better than yours!

A few people were doing that.

With LLMs, anyone can do that. And more.

It's important to frame the scenario correctly. I repeat: I created everything in an afternoon just for giggles, and I challenged myself to write zero lines of code.

> So vibe coding, sure you can create some shitty thing which WORKS (...)

You're somehow blindly labelling a hypothetical output as "shitty", which only serves to show your bias. In the meantime, anyone who is able to churn out a half-functioning MVP in an afternoon is praised as a 10x developer. There's a contrast in there, where the same output is described as shitty or outstanding depending on who does it.

Post reply on HN