Hacker News Reader

Comment by bjackman | Hacker News Reader

I'm slightly surprised to report a 100% score. However, I think I'm actually recognising DALL-E-2's _style_, and not "this picture is CG". It feels more like I'm identifying the work of an artist I'm very familiar with, rather than identifying fundamentally different categories of creator.

I think all it would take to "defeat" me here would be greater variety of high-quality image generation AIs.

I expect in a few years that will be the case, unless the "style" of DALL-E-2 is something fundamental, instead of an artifact of its specific implementation.

View on HN

If you open up the image in a new tab to see the full resolution and look at fine details it's very easy to spot AI ones - AI seems to especially struggle on reflective details, it obviously doesn't know it's meant to be a reflection, so it gets details subtly wrong or weird in the mirror image.

Also anything mechanical is just way off on AI generated things - a car with the fuel door in the middle of the passenger door, a missing tire but you see no axle and nothing makes mechanical sense.

Also, fucked up hands/fingers/letters and such details often give it away

But still, its pretty miraculous.

Interestingly these are the kind of things -fingers, writings, reflections- that also betray the “generative” nature of dreams.

https://lucid.fandom.com/wiki/Reality_check

Also Dalle makes square images so if it’s not square it’s human made

On my phone this was indiscernible

I can see DALL-E-2 stuff spreading around WhatsApp groups like wildfire, masquerading as something else

Even now just selecting Dalle propmpts that output things that look like basic ray tracer tests will probably make it undecidable for anyone not bothering to recrating the scene and chech that it's physically coherent.

well, Theres still plenty telltale signs of AI handwork here. Quasi-faces on places no human would place them or would articulate a detail much better. edge coherence is also very important. Seeing smudges of paint where it doesn't belong at all, lines no human would be able to make and errors only humans make but where AI struggles with.

My point is that Dalle can do things like the Cornell box pretty much perfectly, so if you want to make a test where it's impossible to decide who made it you should sample those type of prompts.

If enough humans on the pool this webpage gets its images from start copying DALL-E-2 effectively that would also "defeat" you.

Reply on news.ycombinator.com