News for hackers. Stuff that matters.

A comment on Show HN: The largest collection of ChatGPT jailbreaks on the internet. Parent comment

Re:Show HN: The largest collection of ChatGPT jailbreaks on ... by og_kalu on Wednesday March 01, 2023 @12:34AM (#34979118)
What if i told you language models are able to generate novel function protein structures based on the purpose you give it ? https://www.nature.com/articles/s41587-022-01618-2

A neural network's training objective is often deceptive. Doesn't matter how simple it seems. What matters is how complex fulfilling the task is, because that is what it will learn. The question you should be asking yourself is, what does it take to generate paragraphs of coherent text that display recursive understanding ?

[ Parent | on HN ]
Re:Show HN: The largest collection of ChatGPT jailbreaks on ... by EGreg on Wednesday March 01, 2023 @08:23AM (#34982089)
In that case, let’s have an LLM learn how to reverse all sha256 hashes? With large accuracy / low loss?

Seems a bit like the “Cargo Cult Science” article by Feynman but done with computers.

[ Parent | on HN ]