Posts

Rome – ACX Meetups Everywhere Spring 2024 2024-03-30T11:19:35.175Z
Agency, LLMs and AI Safety - A First Pass 2023-03-08T15:42:59.123Z
Normie response to Normie AI Safety Skepticism 2023-02-27T13:54:40.249Z
[Preprint] Pretraining Language Models with Human Preferences 2023-02-21T11:44:27.423Z
thesofakillers's Shortform 2023-02-10T17:55:25.188Z

Comments

Comment by Giulio (thesofakillers) on Rome – ACX Meetups Everywhere Spring 2024 · 2024-04-20T10:22:33.045Z · LW · GW

Due to the weather, we're moving this from Saturday to Sunday. Same time same place.

Comment by Giulio (thesofakillers) on thesofakillers's Shortform · 2023-11-15T11:22:31.203Z · LW · GW

why not?

Comment by Giulio (thesofakillers) on thesofakillers's Shortform · 2023-11-15T11:21:59.672Z · LW · GW

I think there can be some parallels to be made between debates on gun control and debates on recent AI regulations

Comment by Giulio (thesofakillers) on thesofakillers's Shortform · 2023-11-14T14:58:39.850Z · LW · GW

Would be nice to have a website collating people's public p(doom) statements

Comment by Giulio (thesofakillers) on Model Organisms of Misalignment: The Case for a New Pillar of Alignment Research · 2023-11-02T20:52:50.480Z · LW · GW

Given the name, I imagine this line of research is inspired by model organism research, although I wonder if a simpler "demonstrations of misalignment" could've been sufficient/better.

Comment by Giulio (thesofakillers) on thesofakillers's Shortform · 2023-04-17T18:32:22.725Z · LW · GW

"don't hate the player, hate the game"

Moloch is "the game"

Comment by Giulio (thesofakillers) on thesofakillers's Shortform · 2023-03-21T09:34:32.366Z · LW · GW

Asteroid movies probably made people more receptive to x-risk from cosmic collisions

maybe we need a movie about x-risk from misaligned AI? something like Ex Machina and/or Her but with more focus on consequences and less robots

idk could be "counterproductive" too I guess

Comment by Giulio (thesofakillers) on thesofakillers's Shortform · 2023-03-05T09:12:05.196Z · LW · GW

It has come to my attention he’s on a sabbatical. That’s great, but his activity (tweets, podcasts) don’t suggest the level of detachment from engagement I was imagining

Comment by Giulio (thesofakillers) on thesofakillers's Shortform · 2023-03-05T01:38:35.544Z · LW · GW

has EY considered taking a break? Like a really long (at least 1 year) vacation where he’s mostly disconnected from AI news and just the world im general. Maybe sail the world or something. Starting to seem like he has given up anyway. Maybe exiting the bubble a bit will allow for new hope (and ideas? motivation?) to form.

Comment by Giulio (thesofakillers) on thesofakillers's Shortform · 2023-03-05T01:36:24.957Z · LW · GW

“Quote tweeting” this:

https://www.lesswrong.com/posts/sJaHghhQXdepZauCc/thesofakillers-s-shortform?commentId=y4NbKHLeDSsppTZ2P

Wonder if it’s worth synchronizing my Twitter with LW shortform.

Probably not. I think I will just handpick which tweets I repost here. Plus some shortform exclusives maybe.

Comment by Giulio (thesofakillers) on thesofakillers's Shortform · 2023-03-03T09:48:44.905Z · LW · GW

is shortform basically just twitter on LW? seems a little like it

Comment by Giulio (thesofakillers) on thesofakillers's Shortform · 2023-01-24T21:43:39.794Z · LW · GW