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

4o Image Generation

openai.com

Post reply on HN
Print view View original

431–440 of 629 posts

Re: 4o Image Generation

#431

Post by icebergonfire »

snickell wrote: post #347
Retr0id wrote: post #346

Earlier quoted context omitted.

Do you have any demo videos?

No, I wasn't planning to post this for a couple weeks, but I saw the comment and was like "eh, why not?". You can watch "sped up" past sessions by other people who used this demo here, which is kind of like a demo video: https://universal.oroborus.org/gallery But the gallery feature isn't really there today, it shows all the "one-click and bounce sessions", and its hard to find signal in the noise. I'll probably subm…

This thing is insanely cool, thanks for creating it.

Re: 4o Image Generation

#432

Post by remuskaos »

widerporst wrote: post #410
eitland wrote: post #388

Earlier quoted context omitted.

Most interesting thing to me is the spelling is correct. I'm not a heavy user of AI or image generation in general, so is this also part of the new release or has this been fixed silently since last I tried?

It very much looks like a side effect of this new architecture. In my experience, text looks much better in recent DALL-E images (so what ChatGPT was using before), but it is still noticeably mangled when printing more than a few letters. This model update seems to improve text rendering by a lot, at least as long as the content is clearly specified. However, when giving a prompt that requires the model to come up wi…

The periodic table is absolutely hilarious, I didn't know LLMs had finally mastered absurdist humor.

Re: 4o Image Generation

#433

Post by noosphr »

mgraczyk wrote: post #427
noosphr wrote: post #426

Earlier quoted context omitted.

Posts like this are terrifying to me. I spend my days coding these tools thinking that everyone using them understands their glaring limitations. Then I see people post stuff like this confidently and I'm taken back to 2005 and arguing that social media will be a net benefit to humanity. The name of the function shows up in: https://github.com/openai/glide-text2im which is where the model probably learned about it.

The tool name is not relevant. It isn't the actual name, they use an obfuscated name. The fact that the model believes it is a tool is good evidence at first glance that it is a tool, because the tool calls are typically IN THE PROMPT. You can literally look at the JavaScript on the web page to see this. You've overcorrected so far in the wrong direction that you think anything the model says must be false, rather th…

>The tool name is not relevant. It isn't the actual name, they use an obfuscated name.

>EDIT: And googling the tool name I see it's already been widely discussed on twitter and elsewhere

I am so confused by this thread.

Re: 4o Image Generation

#434

Post by Fragoel2 »

ibzsy wrote: post #205

Anyone else frightened by this? Seeing meant believing, and now that isnt the case anymore...

In the short term, yes. Over the long run, I think it's good that we move away from the "seeying is believing" model, since that was already abused by bad actors/propaganda Hopefully, not too much chaos until we find another solution.

Re: 4o Image Generation

#435

Post by wegfawefgawefg »

Taek wrote: post #294
rickyhatespeas wrote: post #259

Earlier quoted context omitted.

You're incorrect. 4o was not trained on knowledge of itself so literally can't tell you that. What 4o is doing isn't even new either, Gemini 2.0 has the same capability.

Can you provide a link or screenshot that directly backs this up?

almost all of the models are wrong about their own architecture. half of them claim to be openai and they arent. you cant trust them about this

Re: 4o Image Generation

#437

Post by PufPufPuf »

kilroy123 wrote: post #402
bb88 wrote: post #393

My experience with these announcements is that they're cherry picking the best results from a maybe several hundred or a thousand prompts. I'm not saying that it's not true, it's just "wait and see" before you take their word as gold. I think MS's claim on their quantum computing breakthrough is the latest form of this.

Have you tried it? It's crazy good.

Can it be tried? ChatGPT still uses DALL-E for me.

Re: 4o Image Generation

#438

Post by noosphr »

mgraczyk wrote: post #429
noosphr wrote: post #424

Earlier quoted context omitted.

>You can ask 4o about this yourself. Here's what it said to me: >"So while I’m deeply multimodal in cognition (understanding and coordinating text + image), image generation is handled by a linked latent diffusion model, not an end-to-end token-unified architecture." Models don't know anything about themselves. I have no idea why people keep doing this and expecting it to know anything more than a random con artist o…

This is overly cynical. Models typically do know what tools they have access to because the tool descriptions are in the prompt. Asking a model which tools it has is a perfectly reasonable way of learning what is effectively the content of the prompt. Of course the model may hallucinate, but in this case it takes a few clicks in the dev tools to verify that this is not the case.

>Of course the model may hallucinate, but in this case it takes a few clicks in the dev tools to verify that this is not the case.

I don't know - or care to figure out - how OpenAI does their tool calling in this specific case. But moving tool calls to the end user is _monumentally_ stupid for the latency if nothing else. If you centralize your function calls to a single model next to a fat pipe it means that you halve the latency of each call. I've never build, or seen, a function calling agent that moves the api function calls to client side JS.

Re: 4o Image Generation

#439

Post by wegfawefgawefg »

friendzis wrote: post #401
gorkish wrote: post #188

Earlier quoted context omitted.

I obviously have no idea if they added real or synthetic data to the training set specifically regarding the full-to-the-brim wineglass test, but I fully expect that this prompt is now compromised in the sense that because it is being discussed in the public sphere, it's has inherently become part of the test suite. Remember the old internet adage that the fastest way to get a correct answer online is to post an inco…

> I'm not entirely convinced this type of iterative gap finding and filling is really much different than natural human learning behavior. Take some artisan, I'll go with a barber. The human person is not the best of the best, but still a capable barber, who can implement several styles on any head you throw at them. A client comes, describes certain style they want. The barber is not sure how to implement such a sty…

overfitting vs generalizing

also we all know real people who fail to generalize, and overfit. copycats, potentially even with great skill, no creativity.

Re: 4o Image Generation

#440

Post by wegfawefgawefg »

vlovich123 wrote: post #354
sayamqazi wrote: post #307

Earlier quoted context omitted.

I think there is a critical aspect of human visual learning which machine leanring cant replicate because it is prohibitively expensive. When we look at things as children we are not just looking at a single snapshot. When you stare at an object for a few seconds you have practically injested hundreds of slightly variated images of that object. This gets even more interesting when you take into account real world is…

Then explain blind children? Or blind & deaf children? There's obviously some role senses play in development but there's clearly capabilities at play here that are drastically more efficient and powerful than what we have with modern transformers. While humans learn through example, they clearly need a lot fewer examples to generalize off of and reason against.

they take in many samples of touch data
Post reply on HN