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

ChatGPT Images 2.0

openai.com

Post reply on HN
Print view View original

541–550 of 1001 posts

Re: ChatGPT Images 2.0

#541

Post by minimaxir »

m3kw9 wrote: post #533
minimaxir wrote: post #234

So during my Nano Banana Pro experiments I wrote a very fun prompt that tests the ability for these image generation models to follow heuristics, but still requires domain knowledge and/or use of the search tool: Create a 8x8 contiguous grid of the Pokémon whose National Pokédex numbers correspond to the first 64 prime numbers. Include a black border between the subimages. You MUST obey ALL the FOLLOWING rules for th…

Prob a very unscientific way to test an image model. This would me likely because they have the reasoning turned down and let its instant output takeover

There's no good scientific way to test a closed-source model with both nondeterministic and subjective output.

This example image was generated using the API on high, not the low reasoning version. (it is slow and takes 2 minutes lol)

Re: ChatGPT Images 2.0

#542

Post by cozzyd »

rattlesnakedave wrote: post #442
wewtyflakes wrote: post #232

Earlier quoted context omitted.

A startling number of people either have no arms, one arm, a half of an arm, or a shrunken arm; how odd!

To be fair, the average person has fewer than two arms.

Most people have an ARM in their pockets, nowadays. And possibly on their wrist.

Re: ChatGPT Images 2.0

#543

Post by fizlebit »

Scrolling through those images it just feels like intellectual theft on a massive scale. The only place I think you're going to get genuinely new ideas is from humans. Whether those humans use AI or not I don't care, but the repetitive slop of AI copying the creative output of humans I don't find that interesting. Call me a curmudgeon. I guess humans also create a lot of derivative slop even without AI assistance. If this leads somehow to nicer looking user interfaces and architecture maybe that is good thing. There are a lot of ugly websites, buildings and products.

Re: ChatGPT Images 2.0

#544

Post by crustaceansoup »

m3kw9 wrote: post #533
minimaxir wrote: post #234

So during my Nano Banana Pro experiments I wrote a very fun prompt that tests the ability for these image generation models to follow heuristics, but still requires domain knowledge and/or use of the search tool: Create a 8x8 contiguous grid of the Pokémon whose National Pokédex numbers correspond to the first 64 prime numbers. Include a black border between the subimages. You MUST obey ALL the FOLLOWING rules for th…

Prob a very unscientific way to test an image model. This would me likely because they have the reasoning turned down and let its instant output takeover

If the results are quantifiable/objective and repeatable it's scientific, how is it not scientific?

The reasoning amount is part of the evaluation isn't it?

Re: ChatGPT Images 2.0

#545

Post by justani »

I have a few cases where nano banana fails all the time, even gpt image 2 is failing.

A 3 * 3 cube made out of small cubes, with a small 2 * 2 cube removed from it - https://chatgpt.com/share/69e85df6-5840-83e8-b0e9-3701e92332...

Create a dot grid containing a rectangle covering 4 dots horizontally and 3 dots vertically - https://chatgpt.com/share/69e85e4b-252c-83e8-b25f-416984cf30...

One where Nano banana fails but gpt image 2 worked: create a grid from 1 to 100 and in that grid put a snake, with it's head at 75 and tail at 31 - https://chatgpt.com/share/69e85e8b-2a1c-83e8-a857-d4226ba976...

Re: ChatGPT Images 2.0

#546

Post by s4i »

ndriscoll wrote: post #172
drivebyhooting wrote: post #144

Earlier quoted context omitted.

Repetition rather than novelty is good for learning.

Sure, and she gets that, but at some point she completely memorizes the stories. She also asks if we can get new books at the store, but they don't make 'em that fast.

Isn’t that also a valuable life lesson that some topics/resources are scarce and at some point you need to do something else?

Re: ChatGPT Images 2.0

#547

Post by globular-toast »

wewtyflakes wrote: post #232
simonw wrote: post #37

Earlier quoted context omitted.

I just got a much better version using this command instead, which uses the maximum image size according to https://github.com/openai/openai-cookbook/blob/main/examples... OPENAI_API_KEY="$(llm keys get openai)" \ uv run 'https://raw.githubusercontent.com/simonw/tools/refs/heads/main/python/openai_image.py' \ -m gpt-image-2 \ "Do a where's Waldo style image but it's where is the raccoon holding a ham radio" \ --quali…

A startling number of people either have no arms, one arm, a half of an arm, or a shrunken arm; how odd!

Finding the raccoon was instant. Finding all the weird AI artifacts is more fun. It's quite fascinating really. As usual it looks impressive at a glance but completely falls apart on closer inspection. I also didn't find any jokes, unless maybe the bridge to nowhere or finger posts pointing both ways counts?

Re: ChatGPT Images 2.0

#549

Post by Barbing »

Legend2440 wrote: post #16
samiwami wrote: post #9

do they have anything similar to SynthID, or are they just pretending that problem doesn't exist? I know this is probably mega cherry-picked to look more impressive, but some of the images are terrifyingly realistic. They seem to have put a lot of effort into the lighting.

I think we are just going to have to accept that realistic images can be easily fabricated now. Seeing is not believing anymore, and I don't think SynthID or anything like it can restore that trust in images.

It's going to mess up accountability.

Some politician will be recorded doing something & he'll have his people release a thousand photos/videos of him doing crimes. And they'll say, look, it's a smear campaign.

This is just one stupid example, but people will have better schemes.

Also global coordinated releases of fake content and hypertargeted possibly abusive content. Virtual kidnappings will take off, automated & scaled.

Re: ChatGPT Images 2.0

#550

Post by teruakohatu »

justani wrote: post #545

I have a few cases where nano banana fails all the time, even gpt image 2 is failing. A 3 * 3 cube made out of small cubes, with a small 2 * 2 cube removed from it - https://chatgpt.com/share/69e85df6-5840-83e8-b0e9-3701e92332... Create a dot grid containing a rectangle covering 4 dots horizontally and 3 dots vertically - https://chatgpt.com/share/69e85e4b-252c-83e8-b25f-416984cf30... One where Nano banana fails but…

> A 3 * 3 cube made out of small cubes, with a small 2 * 2 cube removed from it - https://chatgpt.com/share/69e85df6-5840-83e8-b0e9-3701e92332...

It is a little ambiguous (what exactly is a "3x3 cube") but I tried a bunch of variations and I simply could not get any Gemini models to produce the right output.

Post reply on HN