Tech | Visa | Scholarship/School | Info Place

Anthropic How to find a trick to make AI give answers it shouldn’t

If you build it, people will try to destroy it.Sometimes even people architecture What breaks it is stuff. Such is the case at Anthropic, whose latest research shows an interesting vulnerability in current LLM technology. If you keep asking a question, more or less, you might break the guardrails and end up with large language models telling you things they shouldn’t be telling you in the first place. Like how to make a bomb.

Of course, with the advancement of open source AI technology, you can build your own LLM locally and ask whatever you want, but for something more consumer-grade, it’s a question worth thinking about. What’s interesting about AI today is its rapid development and how well (or poorly) we as a species are doing at better understanding what we’re building.

If you allow me to think about it, I wonder if as LLM and other new AI model types get smarter and larger, we’ll see more of the types of questions and issues outlined by Anthropic. Maybe I’m repeating myself. But the closer we get to more general artificial intelligence, the more it should be like a thinking entity rather than a computer that we can program, right? If so, might we have a harder time identifying edge cases to the point where this becomes unfeasible? Anyway, let’s talk about what Anthropic has shared recently.

#Anthropic #find #trick #give #answers #shouldnt

Leave a Reply

Your email address will not be published. Required fields are marked *