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

581–590 of 944 posts

Re: OpenAI O3-Mini

#581

Post by tkgally »

simonw wrote: post #306

I used o3-mini to summarize this thread so far. Here's the result: https://gist.github.com/simonw/09e5922be0cbb85894cf05e6d75ae... For 18,936 input, 2,905 output it cost 3.3612 cents. Here's the script I used to do it: https://til.simonwillison.net/llms/claude-hacker-news-themes...

Borrowing most of Simon’s prompt, I tried the following with o3-mini-high in the chat interface with Search turned on:

“Summarize the themes of the opinions expressed in discussions on Hacker News on January 31 and February 1, 2025, about OpenAI’s release od [sic] ChatGPT o3-mini. For each theme, output a header. Include direct "quotations" (with author attribution) where appropriate. You MUST quote directly from users when crediting them, with double quotes. Fix HTML entities. Go long. Include a section of quotes that illustrate opinions uncommon in the rest of the piece”

The result is here:

https://chatgpt.com/share/679d790d-df6c-8011-ad78-3695c2e254...

Most of the cited quotations seem to be accurate, but at least one (by uncomplexity_) does not appear in the named commenter’s comment history.

I haven’t attempted to judge how accurate the summary is. Since the discussions here are continuing at this moment, this summary will be gradually falling out of date in any case.

Re: OpenAI O3-Mini

#582

Post by foobiekr »

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,…

Have you tried any of the specialty services like Augment? I am curious if they are any better or just snake oil.

Re: OpenAI O3-Mini

#583

Post by scarface_74 »

threecheese wrote: post #358
simonw wrote: post #306

I used o3-mini to summarize this thread so far. Here's the result: https://gist.github.com/simonw/09e5922be0cbb85894cf05e6d75ae... For 18,936 input, 2,905 output it cost 3.3612 cents. Here's the script I used to do it: https://til.simonwillison.net/llms/claude-hacker-news-themes...

I haven’t tried o3, but one issue I struggle with in large context analysis tasks is the LLMs are never thorough. In a task like this thread summarization, I typically need to break the document down and loop through chunks to ensure it actually “reads” everything. I might have had to recurse into individual conversations with some small max-depth and leaf count and run inference on each, and then have some aggregati…

Try Google’s NotebookLM

Re: OpenAI O3-Mini

#584

Post by famouswaffles »

nimithryn wrote: post #523
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 cu…

I mean, do you think this is awful ?

https://pastebin.com/Ja14mt6L

Re: OpenAI O3-Mini

#585

Post by stavros »

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/

Do you have plans to try o3-mini-high as the architect and Sonnet as the model?

Re: OpenAI O3-Mini

#586

Post by bobjordan »

losvedir wrote: post #9
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

What about "o1 Pro mode". Is that just o1 but with more reasoning time, like this new o3-mini's different amount of reasoning options?

I have been paying $200 per month for 01-pro mode and I am very disappointed right now because they have completely replaced the model today. It used to think for 1-5 minutes and deliver an unbelievably useful one-shot answer. Now, it only thinks for 7 seconds just like the 03-mini model and I can't tell the difference in the answers. I hope this is just a day 1 implementation bug but I suspect they have just decided to throw the $200 per month customers under the bus so that they'd have more capacity to launch the 03 model for everybody. I can't tell the difference between the models now and it is definitely not because the free 03 model delivers the quality that 01-pro-mode had! I'm so disappointed!

Re: OpenAI O3-Mini

#587

Post by bobjordan »

ActVen wrote: post #34
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

I really wish they would open up the reasoning effort toggle on o1 API. o1 Pro Mode is still the best overall model I have used for many complex tasks.

Have you tried the o1-pro mode model today, because now it sucks!

Re: OpenAI O3-Mini

#588

Post by liamwire »

mvkel wrote: post #547
zackproser wrote: post #518

Earlier quoted context omitted.

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...

My point was that a prompt that simple could be held and executed very well by sonnet, but all other models (especially reasoning models) crash and burn. It's a 15 line tsx file so context shouldn't be an issue. Makes me wonder if reasoning models are really proper models for coding in existing codebases

Your last point matches what I’ve seen some people (simonw?) say they’re doing currently: using aider to work with two models—one reasoning model as an architect, and one standard LLM as the actual coder. Surprisingly, the results seem pretty good vs. putting everything on one model.

Re: OpenAI O3-Mini

#589

Post by chrismsimpson »

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’ve coded in many languages over the years but reasonably new to the TS/JS/Next world.

I’ve found if you give your prompts a kind long form “stream of consciousness”, where you outline snippets of code in markdown along with contextual notes and then summarise/outline at the end what you actually wish to achieve, you can get great results.

Think a long form, single page “documentation” type prompts that alternate between written copy/contextual intent/description and code blocks. Annotating code blocks with file names above the blocks I’m sure helps too. Don’t waste your context window on redundant/irrelevant information or code, stating a code sample is abridged or adding commented ellipses seems to do the job.

Re: OpenAI O3-Mini

#590

Post by thousand_nights »

simonw wrote: post #306

I used o3-mini to summarize this thread so far. Here's the result: https://gist.github.com/simonw/09e5922be0cbb85894cf05e6d75ae... For 18,936 input, 2,905 output it cost 3.3612 cents. Here's the script I used to do it: https://til.simonwillison.net/llms/claude-hacker-news-themes...

good morning!
Post reply on HN