LESSWRONG
LW

technicalities
999Ω2299640
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No wikitag contributions to display.
Shallow review of technical AI safety, 2024
technicalities6mo10

I hear that you and your band have sold your technical agenda and bought suits. I hear that you and your band have sold your suits and bought gemma scope rigs.

 

(riff on this tweet, which is a riff on the original)

Reply
Shallow review of technical AI safety, 2024
technicalities6mo20

Done, thanks!

Reply1
Are extreme probabilities for P(doom) epistemically justifed?
technicalities1y10

As of two years ago, the evidence for this was sparse. Looked like parity overall, though the pool of "supers" has improved over the last decade as more people got sampled.

There are other reasons to be down on XPT in particular.

Reply1
Least-problematic Resource for learning RL?
Answer by technicalitiesFeb 19, 202420

I like Hasselt and Meyn (extremely friendly, possibly too friendly for you)

Reply
Dalcy's Shortform
technicalities1y10

Maybe he dropped the "c" because it changes the "a" phoneme from æ to ɑː and gives a cleaner division in sounds: "brac-ket" pronounced together collides with "bracket" where "braa-ket" does not. 

Reply
Shallow review of live agendas in alignment & safety
technicalities2y10

It's under "IDA". It's not the name people use much anymore (see scalable oversight and recursive reward modelling and critiques) but I'll expand the acronym.

Reply
Shallow review of live agendas in alignment & safety
technicalities2y32

The story I heard is that Lightspeed are using SFF's software and SFF jumped the gun in posting them and Lightspeed are still catching up. Definitely email.

Reply
Shallow review of live agendas in alignment & safety
technicalities2y10

d'oh! fixed

no, probably just my poor memory to blame

Reply1
Shallow review of live agendas in alignment & safety
technicalities2y10

Yep, no idea how I forgot this. concept erasure!

Reply
Shallow review of live agendas in alignment & safety
technicalities2y30

Interesting. I hope I am the bearer of good news then

Reply
Load More
12curate
6mo
0
193Shallow review of technical AI safety, 2024
Ω
6mo
Ω
35
17"Safety as a Scientific Pursuit" (2024)
1y
3
16Appendices to the live agendas
2y
4
348Shallow review of live agendas in alignment & safety
Ω
2y
Ω
73
105ActAdd: Steering Language Models without Optimization
Ω
2y
Ω
3
91Announcing the Alignment of Complex Systems Research Group
Ω
3y
Ω
20
24Case for emergency response teams
3y
0
44Hinges and crises
3y
7
52Experimental longtermism: theory needs data
3y
0
Load More