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

OpenAI O3-Mini

openai.com

Post reply on HN
Print view View original

531–540 of 944 posts

Re: OpenAI O3-Mini

#531

Post by jwpapi »

zackproser wrote: post #518
mvkel wrote: post #510

I've been using cursor since it launched, sticking almost exclusively to claude-3.5-sonnet because it is incredibly consistent, and rarely loses the plot. As subsequent models have been released, most of which claim to be better at coding, I've switched cursor to it to give them a try. o1, o1-pro, deepseek-r1, and the now o3-mini. All of these models suffer from the exact same "adhd." As an example, in a NextJS app,…

Not trying to be snarky, but the example prompt you provided is about 1/15th the length and detail of prompts I usually send when working with Cursor. I tend to exhaustively detail what I want, including package names and versions because I've been to that movie before...

Yes this works good for me too rather take your time and do the first prompt right

Re: OpenAI O3-Mini

#532

Post by niek_pas »

esafak wrote: post #448
diegocg wrote: post #366

I hope chatgpt reconsiders the naming of their models some time. I have troubles deciding which model is the one I should use.

They release models too often for a new one to be better at everything, so you have to pick the right one for your task.

And that’s exactly where good, recognizable branding comes in.

Re: OpenAI O3-Mini

#533

Post by macNchz »

ChadNauseam wrote: post #522
dhc02 wrote: post #520

Earlier quoted context omitted.

Aider, with o1 or R1 as the architect and Claude 3.5 as the implementer, is so much better than anything you can accomplish with a single model. It's pretty amazing. Aider is at least one order of magnitude more effective for me than using the chat interface in Cursor. (I still use Cursor for quick edits and tab completions, to be clear).

I normally use aider by just typing in what I want and it magically does it. How do I use o1 or R1 to play the role of the "architect"?

You can start it with something like:

    aider --architect --model o1 --editor-model sonnet
Then you'll be in "architect" mode, which first prompts o1 to design the solution, then you can accept it and allow sonnet to actually create the diffs.

Most of the time your way works well—I use sonnet alone 90% of the time, but the architect mode is really great at getting it unstuck when it can't seem to implement what I want correctly, or keeps fixing its mistakes by making things worse.

Re: OpenAI O3-Mini

#534

Post by energy123 »

mvkel wrote: post #510

I've been using cursor since it launched, sticking almost exclusively to claude-3.5-sonnet because it is incredibly consistent, and rarely loses the plot. As subsequent models have been released, most of which claim to be better at coding, I've switched cursor to it to give them a try. o1, o1-pro, deepseek-r1, and the now o3-mini. All of these models suffer from the exact same "adhd." As an example, in a NextJS app,…

Context length possibly. Prompt adherence drops off with context, and anything above 20k tokens is pushing it. I get the best results by presenting the smallest amount of context possible, including removing comments and main methods and functions that it doesn't need to see. It's a bit more work (not that much if you have a script that does it for you), but the results are worth it. You could test in the chatgpt app (or lmarena direct chat) where you ask the same question but with minimal hand curated context, and see if it makes the same mistake.

Re: OpenAI O3-Mini

#535

Post by mordae »

Deegy wrote: post #228
airstrike wrote: post #46

Hopefully this is a big improvement from o1. o1 has been very disappointing after spending sufficient time with Claude Sonnet 3.5. It's like it actively tries to gaslight me and thinks it knows more than I do. It's too stubborn and confidently goes off in tangents, suggesting big changes to parts of the code that aren't the issue. Claude tends to be way better at putting the pieces together in its not-quite-mental-mo…

I've also noticed that with cGPT. That said I often run into a sort of opposite issue with Claude. It's very good at making me feel like a genius. Sometimes I'll suggest trying a specific strategy or trying to define a concept on my own, and Claude enthusiastically agrees and takes us down a 2-3 hour rabbit hole that ends up being quite a waste of time for me to back track out of. I'll then run a post-mortem through…

It's a little sycophant.

But the difference is that it actually asks questions. And also that it actually rolls with what you ask it to do. Other models are stubborn and loopy.

Re: OpenAI O3-Mini

#537

Post by energy123 »

jen729w wrote: post #211

> Testers preferred o3-mini's responses to o1-mini 56% of the time I hope by this they don't mean me, when I'm asked 'which of these two responses do you prefer'. They're both 2,000 words, and I asked a question because I have something to do. I'm not reading them both ; I'm usually just selecting the one that answered first. That prompt is pointless. Perhaps as evidenced by the essentially 50% response rate: it's a…

Then 56% is even more impressive. Example: if 80% choose randomly and 20% choose carefully, that implies an 80% preference rate for o3-mini (0.8*0.2 + 0.5*0.8 = 0.56)

Re: OpenAI O3-Mini

#538

Post by inerte »

zackproser wrote: post #518
mvkel wrote: post #510

I've been using cursor since it launched, sticking almost exclusively to claude-3.5-sonnet because it is incredibly consistent, and rarely loses the plot. As subsequent models have been released, most of which claim to be better at coding, I've switched cursor to it to give them a try. o1, o1-pro, deepseek-r1, and the now o3-mini. All of these models suffer from the exact same "adhd." As an example, in a NextJS app,…

Not trying to be snarky, but the example prompt you provided is about 1/15th the length and detail of prompts I usually send when working with Cursor. I tend to exhaustively detail what I want, including package names and versions because I've been to that movie before...

What works nice also is the text to speech. I find it easier and faster to give more context by talking rather than typing, and the extra content helps the AI to do its job.

And even though the speech recognition fails a lot on some of the technical terms or weirdly named packages, software, etc, it still does a good job overall (if I don’t feel like correcting the wrong stuff).

It’s great and has become somewhat of a party trick at work. Some people don’t even use AI to code that often, and when I show them “hey have you tried this?” And just tell the computer what I want? Most folks are blown away.

Re: OpenAI O3-Mini

#539

Post by esperent »

mvkel wrote: post #510

I've been using cursor since it launched, sticking almost exclusively to claude-3.5-sonnet because it is incredibly consistent, and rarely loses the plot. As subsequent models have been released, most of which claim to be better at coding, I've switched cursor to it to give them a try. o1, o1-pro, deepseek-r1, and the now o3-mini. All of these models suffer from the exact same "adhd." As an example, in a NextJS app,…

Claude uses Shadcn-ui extensively in the web interface, to the point where I think it's been trained to use it over other UI components.

So I think you got lucky and you're asking it to write using a very specific code library that it's good at, because it happens to use it for it's main userbase on the web chat interface.

I wonder if you were using a different component library, or using Svelte instead of React, would you still find Claude the best?

Re: OpenAI O3-Mini

#540

Post by nextworddev »

throw83288 wrote: post #524
anotherpaulg wrote: post #503

For AI coding, o3-mini scored similarly to o1 at 10X less cost on the aider polyglot benchmark [0]. This comparison was with both models using high reasoning effort. o3-mini with medium effort scored in between R1 and Sonnet. 62% $186 o1 high 60% $18 o3-mini high 57% $5 DeepSeek R1 54% $9 o3-mini medium 52% $14 Sonnet 48% $0 DeepSeek V3 [0] https://aider.chat/docs/leaderboards/

What do you expect to come from full o3 in terms of automating software engineering?

o3 (high) might score 80%+
Post reply on HN