News for hackers. Stuff that matters.
Re:Llama 3-V: Matching GPT4-V with a 100x smaller model and ... by alexcnwy on Wednesday May 29, 2024 @02:42AM (#40509166)
the coolest use case i've seen is this https://github.com/ddupont808/GPT-4V-Act
Re:Llama 3-V: Matching GPT4-V with a 100x smaller model and ... by nucleative on Wednesday May 29, 2024 @03:13AM (#40509319)
I feel like this is the beginning of the end for all captchas
Re:Llama 3-V: Matching GPT4-V with a 100x smaller model and ... by udev4096 on Wednesday May 29, 2024 @03:50AM (#40509525)
Image based or any kind of visual captchas will never be extremely effective. I think we will see more of PoW captchas in the upcoming years (just like cloudflare's turnstile captcha)
Re:Llama 3-V: Matching GPT4-V with a 100x smaller model and ... by fennecfoxy on Wednesday May 29, 2024 @08:21AM (#40511162)
I'm not suer about that, can't you give GPT4 a math problem in an image already and have it solve it correctly most of the time?

And these haven't even been trained to defeat captchas/logic problem captchas yet, if it was fine tuned on the general pattern of them I imagine any form of captcha is bust.

Re:Llama 3-V: Matching GPT4-V with a 100x smaller model and ... by mewpmewp2 on Wednesday May 29, 2024 @05:55PM (#40517500)
Not sure about PoW. What about people with slower phones etc?

I don't see how an older smartphone could meaningfully outcompute a spamming infra.

Re:Llama 3-V: Matching GPT4-V with a 100x smaller model and ... by jorvi on Wednesday May 29, 2024 @08:48AM (#40511401)
Twitter / X has a very interesting captcha: you get to see 10 objects that have weird colors and are slightly deformed, and then you have to match them (1 at a time) with another row that has the same objects but seen from a different angle.

Of course eventually this will be defeated too, but for now it seems to work pretty well.