LESSWRONG
LW

Giulio
398120
Message
Dialogue
Subscribe

giuliostarace.com

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No wikitag contributions to display.
1thesofakillers's Shortform
2y
15
AGI Safety & Alignment @ Google DeepMind is hiring
Giulio5mo20

thank you for the post! Are you able to share roughly what the interview/hiring process will be like? E.g. how many stages, duration, etc

Reply
Rome – ACX Meetups Everywhere Spring 2024
Giulio1y10

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

Reply
thesofakillers's Shortform
Giulio2y10

why not?

Reply
thesofakillers's Shortform
Giulio2y3-4

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

Reply
thesofakillers's Shortform
Giulio2y20

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

Reply
Model Organisms of Misalignment: The Case for a New Pillar of Alignment Research
Giulio2y20

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.

Reply
thesofakillers's Shortform
Giulio2y10

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

Moloch is "the game"

Reply
thesofakillers's Shortform
Giulio2y74

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

Reply
thesofakillers's Shortform
Giulio2y*10

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

Reply
thesofakillers's Shortform
Giulio2y20

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.

Reply
Load More
10Language for Goal Misgeneralization: Some Formalisms from my MSc Thesis
1y
0
2Agency, LLMs and AI Safety - A First Pass
2y
0
10Normie response to Normie AI Safety Skepticism
2y
1
12[Preprint] Pretraining Language Models with Human Preferences
2y
0
1thesofakillers's Shortform
2y
15