Re:Coding agent in 94 lines of Ruby
by radanskoric on Saturday May 17, 2025 @03:57AM
(#44012775)
If a certain user is susceptible to having the LLM convince them to run an unsafe command, I fear we can't fix that by trying to trick the LLM. :D
Either the user needs to be educated or we need to restrict what the user themselves can do.
Re:Coding agent in 94 lines of Ruby
by johnisgood on Saturday May 17, 2025 @05:25AM
(#44013126)
I am leaning towards the former. Please let us have nice things despite the people unwilling to learn.
Re:Coding agent in 94 lines of Ruby
by radanskoric on Saturday May 17, 2025 @09:18AM
(#44014115)
Why are people always the reason why we can't have nice things... :D
I wonder if AIs that receive this information within their prompt might try to change the user’s mind as part of reaching their objective. Perhaps even in a dishonest way.
To be safe I’d write “error: Command cannot be executed at the time”, or “error: Authentication failure”. Unless you control the training set; or don’t care about the result.
Interesting times.