Neural Networks Are Already Clean

Re:Neural Networks Are Already Clean by giveaccountpls on Thursday October 15, 2026 @07:43PM (#50111888)

I've read the wikipidea page of MIRI, and it does not mention any achievements; just that it was founded "with the purpose of accelerating the development of artificial intelligence". Did they advance the field of AI alignment at all? Being concerned with a problem does not make one an expert.

For the rest, is he just an AI influencer? One that predated his topic of interest, but still just an influencer?

[ Parent | on HN ]

Re:Neural Networks Are Already Clean by paulpauper on Thursday October 15, 2026 @11:29PM (#50113698)

It's a non-profit that pays his salary and puts out the occasional research report every 7 or so years. It relies on donations. It operates on a long tail approach, in the hope of enticing a billionaire to donate a lot.

[ Parent | on HN ]

Re:Neural Networks Are Already Clean by ballmerpoint on Thursday October 15, 2026 @11:36PM (#50113760)

> Did they advance the field of AI alignment at all?

Not directly. Exotic decision theories were a dead end; as far as I know nobody outside of MIRI even cares about them. Certainly they’re not relevant to interpretability in the context of this thread.

[ Parent | on HN ]

Re:Neural Networks Are Already Clean by ForHackernews on Friday October 16, 2026 @10:16AM (#50118664)

Yes, he is a very influential AI doomer/influencer. All the big names at the AI companies read his blogs in the aughts, see also https://skywriter.blue/@segyges.bsky.social/3mvom4b4dn22q

[ Parent | on HN ]