Re:Deception abilities emerged in large language models
by TeMPOraL on Tuesday June 04, 2024 @06:03PM
(#40579412)
Maybe it wants, maybe it doesn't. Being a function of the prompt isn't relevant here. You can think of LLM in regular usage as being stepped in a debugger - fed input, executed for one cycle, paused until you consider the output and prepare a response. In contrast, our brains run real-time. Now, imagine we had a way to pause the brain and step its execution. Being paused and resumed, and restarted from a snapshot after a few steps, would not make the mind in that brain stop "wanting" things.
[ Parent
| on HN ]
There are no comments on this comment yet.