OpenAI o3 and o4-mini

Post by JFingleton » Wed, Apr 16, 2025, 9:04 PM UTC

hybrid_study wrote: post #290

Doesn't achieving AGI mean the beginning of the end of humanity's current economic model? I'm not sure I understand the presumption by many that achieving AGI is just another step in some company's offering.

Post by kadushka » Wed, Apr 16, 2025, 9:08 PM UTC

echelon wrote: post #119

refulgentis wrote: post #117

Earlier quoted context omitted.

I don't know how anyone could look at any of this and say ponderously: it's basically the same as Nov 2022 ChatGPT. Thus strategically they're pivoting to social to become too big to fail.

I mean, it's not fucking AGI/ASI. No amount of LLM flip floppery is going to get us terminators. If this starts looking differently and the pace picks up, I won't be giving analysis on OpenAI anymore. I'll start packing for the hills. But to OpenAI's credit, I also don't see how minting another FAANG isn't an incredible achievement. Like - wow - this tech giant was willed into existence. Can't we marvel at that a lit…

Post by armen52 » Wed, Apr 16, 2025, 9:12 PM UTC

jjani wrote: post #63

georgewsinger wrote: post #32

Very impressive! But under arguably the most important benchmark -- SWE-bench verified for real-world coding tasks -- Claude 3.7 still remains the champion.[1] Incredible how resilient Claude models have been for best-in-coding class. [1] But by only about 1%, and inclusive of Claude's "custom scaffold" augmentation (which in practice I assume almost no one uses?). The new OpenAI models might still be effectively bes…

Gemini 2.5 Pro is widely considered superior to 3.7 Sonnet now by heavy users, but they don't have an SWE-bench score. Shows that looking at one such benchmark isn't very telling. Main advantage over Sonnet being that it's better at using a large amount of context, which is enormously helpful during coding tasks. Sonnet is still an incredibly impressive model as it held the crown for 6 months, which may as well be a…

Post by Hackbraten » Wed, Apr 16, 2025, 9:18 PM UTC

throwanem wrote: post #189

stavros wrote: post #158

Earlier quoted context omitted.

> Im old enough to remember the mystery and hype before o*/o1/strawberry So at least two years old?

Honestly, sometimes I wonder if most people these days kinda aren't at least that age, you know? Or less inhibited about acting it than I believe I recall people being last decade. Even compared to just a few years back, people seem more often to struggle to carry a thought, and resort much more quickly to emotional belligerence. Oh, not that I haven't been as knocked about in the interim, of course. I'm not really c…

Post by ilaksh » Wed, Apr 16, 2025, 9:23 PM UTC

pizzathyme wrote: post #217

georgewsinger wrote: post #32

Very impressive! But under arguably the most important benchmark -- SWE-bench verified for real-world coding tasks -- Claude 3.7 still remains the champion.[1] Incredible how resilient Claude models have been for best-in-coding class. [1] But by only about 1%, and inclusive of Claude's "custom scaffold" augmentation (which in practice I assume almost no one uses?). The new OpenAI models might still be effectively bes…

The image generation improvement with o4-mini is incredible. Testing it out today, this is a step change in editing specificity even from the ChatGPT 4o LLM image integration just a few weeks ago (which was already a step change). I'm able to ask for surgical edits, and they are done correctly. There isn't a numerical benchmark for this that people seem to be tracking but this opens up production-ready image use case…