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

521–530 of 944 posts

Re: OpenAI O3-Mini

#521

Post by dutchbookmaker »

echelon wrote: post #20
pookieinc wrote: post #8

Can't wait to try this. What's amazing to me is that when this was revealed just one short month ago, the AI landscape looked very different than it does today with more AI companies jumping into the fray with very compelling models. I wonder how the AI shift has affected this release internally, future releases and their mindset moving forward... How does the efficiency change, the scope of their models, etc.

There's no moat, and they have to work even harder. Competition is good.

It is still curious though as far as what is actually being automated?

I find huge value in these models as an augmentation of my intelligence and as a kind of cybernetic partner.

I can't think of anything that can actually be automated though in terms of white collar jobs.

The white collar model test case I have in mind is a bank analyst under a bank operations manger. I have done both in the past but there is something really lacking with the idea of the operations manager replacing the analyst with a reasoning model even though DeepSeek annihilates every bank analyst reasoning I ever worked with right now.

If you can't even arbitrage the average bank analyst there might be these really non-intuitive no AI arbitrage conditions with white color work.

Re: OpenAI O3-Mini

#522

Post by ChadNauseam »

dhc02 wrote: post #520
jvanderbot wrote: post #515

Earlier quoted context omitted.

I've found cursor to be too thin a wrapper. Aider is somehow significantly more functional. Try that.

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"?

Re: OpenAI O3-Mini

#523

Post by nimithryn »

famouswaffles wrote: post #121

R1 seems to be the only of these reasoning models that seem to have had gains in the creative writing side.

Am I the only one who thinks that R1 is awful at creative writing? I've seen a lot of very credulous posts on twitter that are super excited about excerpts written by DeepSeek that I think are absolutely absymal. Am I alone in this? Maybe people have very different tastes than I do?

(I have no formal training in creative writing, though I do read a lot of literature. Not claiming my tastes are superior - genuinely curious if other people disagree).

Re: OpenAI O3-Mini

#524

Post by throw83288 »

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?

Re: OpenAI O3-Mini

#525

Post by dwaltrip »

dhc02 wrote: post #520
jvanderbot wrote: post #515

Earlier quoted context omitted.

I've found cursor to be too thin a wrapper. Aider is somehow significantly more functional. Try that.

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 haven't tried aider in quite a while, what does it mean to use one model as an architect and another as the implementer?

Re: OpenAI O3-Mini

#526

Post by throw83288 »

vok wrote: post #404

Well, o3-mini-high just successfully found the root cause of a seg fault that o1 missed: mistakenly using _mm512_store_si512 for an unaligned store that should have been _mm512_storeu_si512.

How do I avoid the angst about this stuff as a student in computer science? I love this field but frankly I've been at a loss since the rapid development of these models.

Re: OpenAI O3-Mini

#527

Post by torben-friis »

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,…

My experience with cursor and sonnet is that it is relatively good at first tries, but completely misses the plot during corrections.

"My attempt at solving the problem contains a test that fails? No problem, let me mock the function I'm testing, so that, rather than actually run, it returns the expected value!"

It keeps doing that kind of shenanigans, applying modifications that solve the newly appearing problem while screwing the original attempt's goal.

I usually get much better results from regular chatgpt copying and pasting, the trouble being that it is a major pain to handle the context window manually by pasting relevant info and reminding what I think is being forgotten.

Re: OpenAI O3-Mini

#528

Post by Terretta »

dwaltrip wrote: post #525
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 haven't tried aider in quite a while, what does it mean to use one model as an architect and another as the implementer?

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 code editing benchmark. Using o1-preview as the Architect with either DeepSeek or o1-mini as the Editor produced the SOTA score of 85%. Using the Architect/Editor approach also significantly improved the benchmark scores of many models, compared to their previous “solo” baseline scores (striped bars).

https://aider.chat/2024/09/26/architect.html

Re: OpenAI O3-Mini

#529

Post by simonw »

Now that the dust is settling a little bit, I have published my notes so far on o3-mini here: https://simonwillison.net/2025/Jan/31/o3-mini/

To save you the click: I think the most interesting things about this model are the price - less than half that of GPT-4o while being better for many things, most notably code - and the increased length limits.

200,000 tokens input and 100,000 output (compared to 128k/16k for GPT-4o and just 8k for DeepSeek R2 and Claude 3.5 on output) could open up some interesting new applications, especially at that low price.

Re: OpenAI O3-Mini

#530

Post by jwpapi »

torben-friis wrote: post #527
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,…

My experience with cursor and sonnet is that it is relatively good at first tries, but completely misses the plot during corrections. "My attempt at solving the problem contains a test that fails? No problem, let me mock the function I'm testing, so that, rather than actually run, it returns the expected value!" It keeps doing that kind of shenanigans, applying modifications that solve the newly appearing problem whi…

Yes it’s usually worth it to try to write a really good first prompt
Post reply on HN