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

931–940 of 944 posts

Re: OpenAI O3-Mini

#931

Post by dhc02 »

lukas099 wrote: post #617
Terretta wrote: post #528

Earlier quoted context omitted.

Aider now has experimental support for using two models to complete each coding task: - An Architect model is asked to describe how to solve the coding problem. - An Editor model is given the Architect’s solution and asked to produce specific code editing instructions to apply those changes to existing source files. Splitting up “code reasoning” and “code editing” in this manner has produced SOTA results on aider’s c…

Probably gonna show a lot of ignorance here, but isn’t that a big part of the difference between our brains and AI? That instead of one system, we are many systems that are kind of sewn together? I secretly think AGI will just be a bunch of different specialized AIs working together.

Efficient and effective organizations work this way, too: a CEO to plan in broad strokes, employees to implement that vision in specific ways, and managers to make sure their results match expectations.

Re: OpenAI O3-Mini

#932

Post by dhc02 »

nprateem wrote: post #658
cruffle_duffle wrote: post #568

Earlier quoted context omitted.

I really want to see how apps created this way scale to large codebases. I’m very skeptical they don’t turn into spaghetti messes. Coding is basically just about the most precise way to encapsulate a problem as a solution possible. Taking a loose English description and expanding it into piles of code is always going to be pretty leaky no matter how much these models spit out working code. In my experience you have t…

The worst thing you can do with aider is let it autocommit to git. As long as you review each set of changes you can stop it going nuts. I have a codebase maybe 3-500k lines which is in good shape because of this. I also normally just add the specific files I need to the chat and give it 1-2 sentences for what to do. It normally does the right thing (sonnet obviously).

Yes! Turn off autocommit, everyone! Review and test, then git commit.

Re: OpenAI O3-Mini

#933

Post by dhc02 »

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,…

I'm going to give you a video to watch. It's not mine, and I don't know much about this particular youtuber, but it really transformed how I think about writing and structuring the prompts I use, which solved problems similar to what you're describing here.

https://youtu.be/y_ywOVQyafE?si=IvKjy7QUYgxGPNgD

PS (I have not bought the guy's course and have no idea whether it's any good)

Re: OpenAI O3-Mini

#934

Post by WhitneyLand »

YeGoblynQueenne wrote: post #930
WhitneyLand wrote: post #926

Earlier quoted context omitted.

Yeah sure there’s lots of research on reasoning. The papers I’ve seen that make claims about it are usually pretty precise about what it means in the context of that work and that specific claim, at least in the hard sciences listed.

I'm complaining because I haven't seen any such papers. Which ones do you have in mind?

Examples go back 50 years, across many of the disciplines you’ve mentioned, but to throw out one that’s recent, on topic, and highly cited, there’s:

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models https://arxiv.org/pdf/2501.19201

It effectively treats “reasoning” as the ability to generate intermediate steps leading to a correct conclusion.

Now, is this valid reasoning? Well, depends on the claim and the definition of reasoning.

When someone just says AI can’t reason, I could argue for or against that depending on the specifics. It’s not enough to just say yes or no.

Re: OpenAI O3-Mini

#935

Post by YeGoblynQueenne »

WhitneyLand wrote: post #934
YeGoblynQueenne wrote: post #930

Earlier quoted context omitted.

I'm complaining because I haven't seen any such papers. Which ones do you have in mind?

Examples go back 50 years, across many of the disciplines you’ve mentioned, but to throw out one that’s recent, on topic, and highly cited, there’s: Chain-of-Thought Prompting Elicits Reasoning in Large Language Models https://arxiv.org/pdf/2501.19201 It effectively treats “reasoning” as the ability to generate intermediate steps leading to a correct conclusion. Now, is this valid reasoning? Well, depends on the clai…

Thanks for the link.

>> It effectively treats “reasoning” as the ability to generate intermediate steps leading to a correct conclusion.

Is "effectively" the same as "pretty precise" as per your previous comment? I don't see that because I searched the paper for all occurrences of "reasoning" and noticed two things: first that while the term is used to saturation there is no attempt to define it even informally, let alone precisely; and second that I could have replaced "reasoning" with any buzzword of the day and it would not change the impact of the paper. As far as I can tell the paper uses "reasoning" just because it happens to be what's currently trending in LLM circles.

And still of course no attempt to engage with the common understanding of reasoning I discuss above, or any hint that the authors are aware of it.

Sorry to be harsh, but you promised "examples that go back 50 years" and this is the kind of thing I've seen consistently in the last 15 or so.

Re: OpenAI O3-Mini

#936

Post by ttroyr »

eagleinparadise wrote: post #553
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,…

Cursor is also very user-unfriendly in providing alternative models to use in composer (agent). There's a heavy reliance on Anthrophic for cursor. Try using Gemini thinking with Cursor. It barely works. Cmd-k outputs the thinking into the code. Its unusable in chat because the formatting sucks. Is there some relationship between Cursor and Anthropic, i wonder. Plenty of other platforms seem very eager to give users m…

Originally, actually there was a relationship between Cursor & OpenAI. Something like Cursor was supported by the OpenAI startup fund. So Cursor seems to have branched out. I think they are just emphasizing the models they find most effective. I'm surprised they haven't (apparently) incorporated Claude prompt caching yet for Sonnet.

Re: OpenAI O3-Mini

#937

Post by WhitneyLand »

YeGoblynQueenne wrote: post #935
WhitneyLand wrote: post #934

Earlier quoted context omitted.

Examples go back 50 years, across many of the disciplines you’ve mentioned, but to throw out one that’s recent, on topic, and highly cited, there’s: Chain-of-Thought Prompting Elicits Reasoning in Large Language Models https://arxiv.org/pdf/2501.19201 It effectively treats “reasoning” as the ability to generate intermediate steps leading to a correct conclusion. Now, is this valid reasoning? Well, depends on the clai…

Thanks for the link. >> It effectively treats “reasoning” as the ability to generate intermediate steps leading to a correct conclusion. Is "effectively" the same as "pretty precise" as per your previous comment? I don't see that because I searched the paper for all occurrences of "reasoning" and noticed two things: first that while the term is used to saturation there is no attempt to define it even informally, let…

The point is there has to be meaning for reasoning. I think the claim in this paper is very clear and the results are shown decisively.

Research papers relating to reasoning approach and define it in many ways but crucially, the good ones offer a testable claim.

Simply saying “models can’t reason” is ambiguous to the point of being unanswerable.

Re: OpenAI O3-Mini

#938

Post by winrid »

Legend2440 wrote: post #878
winrid wrote: post #374

Earlier quoted context omitted.

There isn't one, unless they fixed it today. Just a down arrow to change the model.

Try clearing your cache, the button has always been there for me.

just reproduced this, not sure what button it is, I think page up? but it removes the sidebar, messes up the layout, and no obv way to fix.

Re: OpenAI O3-Mini

#939

Post by ecopipe »

silverlake wrote: post #325

O3-mini solved this prompt. DeepSeek R1 had a mental breakdown. The prompt: “Bob is facing forward. To his left is Ann, to his right is Cathy. Ann and Cathy are facing backwards. Who is on Ann’s left?”

https://chatgpt.com/share/67a32b47-18fc-8003-9e18-085f9fad72...

o3-mini-high failed at the solution for me.

Re: OpenAI O3-Mini

#940

Post by jes5199 »

usaar333 wrote: post #81
sss111 wrote: post #3

So far, it seems like this is the hierarchy o1 > GPT-4o > o3-mini > o1-mini > GPT-4o-mini o3 mini system card: https://cdn.openai.com/o3-mini-system-card.pdf

For non-stem perhaps. For math/coding problems, o3 mini is tied if not better than o1.

I spent some time yesterday struggling with o3-mini-high trying to do a trigonometry problem, we went round and round and could not solve it. o1 solved it in one shot.
Post reply on HN