This is incredibly impressive, but it's still theft of assets.
4o Image Generation
331–340 of 629 posts
Re: 4o Image Generation
#332Earlier quoted context omitted.
As a user, images feel slightly slower but comparable to the previous generation. Given the significant quality improvement, it's a fair trade-off. Overall, it feels snappy, and the value justifies a higher price.
[flagged]
I just gave quick feedback on the new release. How should I be writing it?
If anything, your feedback is of low value.
Re: 4o Image Generation
#333Earlier quoted context omitted.
The problem now is we don't know if people mistake dall-e for the new multimodal gpt4o output, they really should've made that clearer.
I’m using 4o and it gets time wrong a decent chunk but doesn’t get anything else in the prompt incorrect. I asked for the clock to be 4:30 but got 10:10. OpenAI pro account.
Shouldn't reasoning make the clock work though.
Why does it sound like this isn't reasoning on images directly but rather just dall e as some other comment said , I will type the name of the person here (coder543)
Re: 4o Image Generation
#334Still failing the wine glass test, https://imgur.com/a/aS8e0UY
Worked for me with a clarification. Looks pretty great, actually. https://imgur.com/a/V8eQWi6
Re: 4o Image Generation
#335Earlier quoted context omitted.
I tried and it failed repeatedly (like actual error messages): > It looks like there was an error when trying to generate the updated image of the clock showing 5:03. I wasn’t able to create it. If you’d like, you can try again by rephrasing or repeating the request. A few times it did generate an image but it never showed the right time. It would frequently show 10:10 for instance.
If it tried and failed repeatedly, then it was prompting DALL-E, looking at the results, then prompting DALL-E again, not doing direct image generation.
So it's not doing what they are saying/ advertising, I think you are onto something big then
Re: 4o Image Generation
#336What's important about this new type of image generation that's happening with tokens rather than with diffusion, is that this is effectively reasoning in pixel space. Example: Ask it to draw a notepad with an empty tic-tac-toe, then tell it to make the first move, then you make a move, and so on. You can also do very impressive information-conserving translations, such as changing the drawing style, but also stuff l…
> truly generative UI, where the model produces the next frame of the app
I built this exact thing last month, demo: https://universal.oroborus.org (not viable on phone for this demo, fine on tablet or computer)
Also see discussion and code at: http://github.com/snickell/universal
I wasn't really planning to share/release it today, but, heck, why not.
I started with bitmap-style generative image models, but because they are still pretty bad at text (even this, although it’s dramatically better), for early-2025 it’s generating vector graphics instead. Each frame is an LLM response, either as an svg or static html/css. But all computation and transformation is done by the LLM. No code/js as an intermediary. You click, it tells the LLM where you clicked, the LLM hallucinates the next frame as another svg/static-html.
If it ran 50x faster it’d be an absolutely jaw dropping demo. Unlike "LLMs write code", this has depth. Like all programming, the "LLMs write code" model requires the programmer or LLM to anticipate every condition in advance. This makes LLM written "vibe coded" apps either gigantic (and the llm falls apart) or shallow.
In contrast, as you use universal, you can add or invent features ranging from small to big, and it will fill in the blanks on demand, fairly intelligently. If you don't like what it did, you can critique it, and the next frame improves.
Its agonizingly slow in 2025, but much smarter and in weird ways less error prone than using the LLM to generate code that you then run: just run computation via the LLM itself.
You can build pretty unbelievable things (with hallucinated state, granted) with a few descriptive sentences, far exceeding the capabilities you can “vibe code” with the description. And it never gets lost in its rats nest of self generated garbage code because… there is no code to in.
Code is medium with a surprisingly strong grain. This demo is slow, but SO much more flexible and personally adaptable than anything I’ve used where the logic is implemented cia a programming language.
I don’t love this as a programmer, but my own use of the demo makes me confident that programming languages as a category will have a shelf life if LLM hardware gets fast, cheap and energy efficient.
I suspect LLMs will generate not programming language code, but direct wasm or just machine code on the fly for things that need faster traction than they can draw a frame, but core logic will move out of programming languages (not even llm written code). Maybe similar to the way we bind to low level fast languages but a huge percentage of “business” logic is written in relatively slower languages.
FYI, I may not be able to afford the credits if too many people visit, I put a a $1000 of credits on this, we'll see if that lasts. This is claude 3.7, I tried everything else, a claude had the visual intelligence today. IMO this is a much more compelling glance at the future than coding models. Unfortunately, generating an SVG per click is pricey, each click/frame costs me about $0.05. I’ll fund this as far as I can so folks can play with it.
Anthropic? You there? Wanna throw some credits at an open source project doing something that literally only works on claude today? Not just better, but “only Claude 3.7 can show this future today?”. I’d love for lots more people to see the demo, but I really could use an in-kind credit donation to make this viable. If anyone at anthropic is inspired and wants to hook me up: snickell@alumni.stanford.edu. Very happy to rep Claude 3.7 even more than I already do.
I think it’s great advertising for Claude. I believe the reason Claude seems to do SO much better at this task is, one it shows far greater spatial intelligence, and two, I distract they are the only state of the art model intentionally training on SVG.
Re: 4o Image Generation
#337Visual internet content is completely over. Pack it up
For starters, this completely blocks generation of anything remotely related to copy-protected IPs, which may actually be a saving grace for some creatives. There's a lot of demand for fanart of existing characters, so until this type of model can be run locally, the legal blocks in place actually give artists some space to play in where they don't have to compete with this. At least for a short while.
Despite likely being trained on and stealing from copy protected ips? Not sure if they've changed their approach to training data
Re: 4o Image Generation
#338Earlier quoted context omitted.
If it tried and failed repeatedly, then it was prompting DALL-E, looking at the results, then prompting DALL-E again, not doing direct image generation.
So it's not doing what they are saying/ advertising, I think you are onto something big then
No... OpenAI said it was "rolling out". Not that it was "already rolled out to all users and all servers". Some people have access already, some people don't. Even people who have access don't have it consistently, since it seems to depend on which server processes your request.
Re: 4o Image Generation
#339question i have is when do we get an opensource version of this form of image generation will we see diffusion models moving to this space
Re: 4o Image Generation
#340I tried a few of the prompts and the results I see are far worse than the examples provided. Seems like there will be some room for artists yet in this brave new world.
It hasn't actually rolled out to everyone yet in chat. You'll have to try it on sora to be sure.