My work (strategy research, conceptual stuff) at Forethought gets blocked reasonably often (though I haven’t tried jailbreaking techniques) in my 5 or so days of using Fable.
I’m sure I’m not tripping up the cyber safeguards or AI R&D safeguards. I think occasionally the false positives are due to bio though not all of them.
Note that this is just reviewing docs, and thinking things through, not stuff like certain types of evals for superpersuasion (which I expect to be even worse).
I got blocked today for asking Fable about this Forethought piece, specifically the point about the human brain being undertrained. I suspect it must just flag on anything RSI-related because otherwise this seems really innocuous.
My work (strategy research, conceptual stuff) at Forethought gets blocked reasonably often (though I haven’t tried jailbreaking techniques) in my 5 or so days of using Fable.
I’m sure I’m not tripping up the cyber safeguards or AI R&D safeguards. I think occasionally the false positives are due to bio though not all of them.
Note that this is just reviewing docs, and thinking things through, not stuff like certain types of evals for superpersuasion (which I expect to be even worse).
I got blocked today for asking Fable about this Forethought piece, specifically the point about the human brain being undertrained. I suspect it must just flag on anything RSI-related because otherwise this seems really innocuous.
Oh that might be the bio filters.