New ask Hacker News story: Ask HN: How dangerous is Auto-GPT?

Ask HN: How dangerous is Auto-GPT?
3 by manx | 3 comments on Hacker News.
I'm talking about this project: https://ift.tt/Dbp1nQk It puts LLM's programming capabilities in a feedback loop with the real world in order to achieve arbitrary goals. In my opinion, this has the potential to become a very powerful and therefore dangerous tool. I fear that people with both good and bad intentions give commands that do large scale harm. How do you see it?

Comments