Posts

Thoughts on the Feasibility of Prosaic AGI Alignment? 2020-08-21T23:25:09.895Z

Comments

Comment by iamthouthouarti on Thoughts on the Feasibility of Prosaic AGI Alignment? · 2020-09-03T21:49:09.612Z · LW · GW

The most glaring argument that I could see raised against Christiano’s IDA is that it assumes a functioning AGI would already be developed before measures are taken to make it corrigible. At the same time though, that argument may very well be due to misunderstanding on my part. It’s also possible that MIRI would prefer that the field prioritize over seemingly preparing for non-FOOM scenarios. But I don’t understand how it couldn’t “possibly, possibly, possibly work”.

Comment by iamthouthouarti on Thoughts on the Feasibility of Prosaic AGI Alignment? · 2020-09-01T23:56:16.236Z · LW · GW

I’m a little confused though. I’m aware of Yudkowsky’s misgivings regarding the possible failings of prosaic AGI alignment, but I’m not sure where he states it to be border-line impossible or worse. Also, when you refer to MIRI being highly pessimistic of prosaic AGI alignment, are you referring to the organization as a whole, or a few key members?

I also don’t understand why this disparity of projections exists. Is there a more implicit part of the argument that neither party (Paul Christiano and MIRI) haven’t publicly adressed?

EDIT: Is the argument more so that it isn't currently possible due to a lack of understanding regarding what corrigibility even is, without entertaining how possible it might be some years down the line?

Comment by iamthouthouarti on Thoughts on the Feasibility of Prosaic AGI Alignment? · 2020-08-23T17:45:55.546Z · LW · GW

Interesting, but what is the probability you assign to this chain of events? Just as well, the probability you would assign to the advent of transformative AI (AGI) being prosaic- as in its achieved by scaling existing architectures with more compute and better hardware?

Comment by iamthouthouarti on Thoughts on the Feasibility of Prosaic AGI Alignment? · 2020-08-23T17:42:28.820Z · LW · GW

Thanks for the reply!

Comment by iamthouthouarti on Forecasting Thread: AI Timelines · 2020-08-23T15:58:13.469Z · LW · GW

Just as well, I’m also less confident that shorter timelines are congruent with a high, irreducible probability of failure.

EDIT: If doom is instead congruent simply with the advent of Prosaic AGI, then I still disagree- even moreso, actually.

Comment by iamthouthouarti on Forecasting Thread: AI Timelines · 2020-08-23T15:33:20.426Z · LW · GW

I’m somewhat confused as to how slightly more confident, and slightly less confident equate to doom- which is a pretty strong claim imo.

Comment by iamthouthouarti on Thoughts on the Feasibility of Prosaic AGI Alignment? · 2020-08-22T08:48:26.448Z · LW · GW

Thank you for the reply!

Comment by iamthouthouarti on Developmental Stages of GPTs · 2020-08-21T16:31:06.906Z · LW · GW

Hm, I wonder, since you’d previously prefaced that your own objections towards Paul Christiano’s Iterated Amplification proposals may have stemmed from your own misunderstanding of them. In the two years since you’ve raised these objections, do you continue to hold this position from an epistemological status of having spoken with Christiano on this further? I noticed that he had responded to some of your objections (I forget which post), but you had never responded back. Was this a case of agreeing to disagree, or did you two discuss this further in private?