News for hackers. Stuff that matters.

piotr93

Re:Computing Inside an AI on Sunday December 15, 2024 @07:24AM (#42423067)
Woah super interesting, I didn't know about this. Will def read it! Seems like I was wrong?
Re:Computing Inside an AI on Sunday December 15, 2024 @05:19AM (#42422664)
The only computations that an LLM does are backprops and forward passes. It can not run any arbitrary program description. Yes, it will hallucinate your program's output if you feed it some good enough starting prompt. But that's it.
Re:Computing Inside an AI on Sunday December 15, 2024 @05:10AM (#42422634)
Yes an llm could do it since it can predict the next token for pretty much anything. But what's the error margin you are ready to tolerate?
Re:Programming Zero Knowledge Proofs: From Zero to Hero on Monday September 02, 2024 @02:30AM (#41423093)
A signature is a zkp. So your example is also a good example :)