As a useful exercise, I would advise asking yourself this question first, and thinking about it for five minutes (using a clock) with as much genuine intent to argue against your idea as possible. I might be overestimating the amount of background knowledge required, but this does feel solvable with info you already have.
ROT13: Lbh lbhefrys unir cbvagrq bhg gung n fhssvpvragyl cbjreshy vagryyvtrapr fubhyq, va cevapvcyr, or noyr gb pbaivapr nalbar bs nalguvat. Tvira gung, jr pna'g rknpgyl gehfg n fgengrtl gung n cbjreshy NV pbzrf hc jvgu hayrff jr nyernql gehfg gur NV. Guhf, jr pna'g eryl ba cbgragvnyyl hanyvtarq NV gb perngr n cbyvgvpny fgengrtl gb cebqhpr nyvtarq NV.
Thanks for the response. I did think of this objection, but wouldn't it be obvious if the AI were trying to engineer a different situation than the one requested? E.g., wouldn't such a strategy seem unrelated and unconventional?
It also seems like a hypothetical AI with just enough ability to generate a strategy for the desired situation would not be able to engineer a strategy for a different situation which would both work, and deceive the human actors. As in, it seems the latter would be harder and require an AI with greater ability.
0
hi, i've been learning about alignment and am new to lesswrong. here's my question.
there seems to be a consensus here that AI couldn't be used to solve the problem of AI control per se. that said, is there any discussion or literature on whether a future AI might be able to generate a very impactful political strategy which, if enacted, would engineer a sociopolitical situation where humans have better prospects to solve the problems around AGI?
this question came to my mind in discussing how it seems that, in principle, there should be a way to string together words (and tone, body language, etc) to convince anyone of anything. likewise, it seems there are in principle sequences of actions which would change society/culture to any arbitrary state. however, most of these strategies are far outside the range of what a human could come up with; but a smarter AI might be able to come up with them, or in general have very intelligent ideas humans can't come up with, as Robert Miles helped illustrate to me in this video (https://youtu.be/L5pUA3LsEaw?t=359).