←back to thread

425 points sfarshid | 4 comments | | HN request time: 0s | source
1. efitz ◴[] No.45009469[source]
In one instance, the agent actually used pkill to terminate itself after realizing it was stuck in an infinite loop.

That is pretty awesome and not something I would have expected from an agent; it hints (but does not prove) that it has some awareness of its own workings.

replies(1): >>45009510 #
2. taberiand ◴[] No.45009510[source]
It hints that a suitable auto completion of the input prompt is to output a pkill command
replies(1): >>45010024 #
3. salomonk_mur ◴[] No.45010024[source]
We, too, are just auto-complete, next-token machines.
replies(1): >>45010838 #
4. seba_dos1 ◴[] No.45010838{3}[source]
We are auto-complete next-token machines, but plastic and attached to many other not less important subsystems, which is a crucial difference.