jelly @cat9283

linktr.ee/cat9283 Joined March 2026

Tweets

16
Followers

10
Following

126
Likes

3K

jelly @cat9283

2 weeks ago

@daedalovecat huh i'm confused, RH hasn't been solved yet which should make amount of (solved) RH-equivalents be much lower than 6.9, 6.9 is way too high, unless i'm misunderstanding the term somehow

0 0 0 5 0

View Details

jelly @cat9283

2 weeks ago

@williawa i'm curious how so

1 0 0 62 1

View Details

keltan @Actuallykeltan

3 weeks ago

These are the end credits for the simulation

6 7 60 3K 23

View Details

jelly @cat9283

3 weeks ago

@TetraspaceWest meow

0 0 3 159 0

View Details

jelly @cat9283

3 weeks ago

@wrestling_ugly @captgouda24 Possible solutions are using a bounded utility function, abandoning the independence axiom in VNM rationality, or abandoning expected utility altogether

1 0 1 34 0

View Details

@wrestling_ugly @captgouda24 The issue I think is using an unbounded utility function, and it's proven (lesswrong.com/posts/hbmsW2k9…) that having such a utility function leads to undesirable properties that makes it better off not to use it at all

1 0 1 70 0

View Details

jelly @cat9283

4 weeks ago

@Nitit2001 @_Mira___Mira_ ZFC is stronger than PA and independence in ZFC implies independence in PA

1 0 1 135 0

View Details

David Manheim ✈️ Montreal, Oct 26-28 @davidmanheim

a month ago

The only way for auditors to have full independence from the companies is ensuring they are entirely causally separated; we must immediately launch AI companies and auditors at the speed of light away from each other to ensure they cannot have any connections!

2 1 6 811 0

View Details

jelly @cat9283

a month ago

@AISafetyMemes @liron that's a really huge update

0 0 2 174 1

View Details

jelly @cat9283

a month ago

@fluxxrider cool!

0 0 0 97 0

View Details

jelly @cat9283

2 months ago

@fluxxrider @tszzl it could be the church-turing thesis

0 0 0 60 0

View Details

Aella @Aella_Girl

2 months ago

it's getting harder for me to understand people who *don't* think there's a very serious risk of AI takeover very soon.

323 61 2K 156K 148

View Details

jelly @cat9283

2 months ago

lesswrong.com/posts/qTNm8qzq…

0 0 1 62 0

View Details

jelly @cat9283

2 months ago

lesgo agent foundations strikes again

1 0 1 98 0

View Details

jelly @cat9283

2 months ago

@Actuallykeltan The first image really doesn't look like a compass to me, and the abstract LW art style isn't like the river map at all

0 0 1 204 0

View Details

Peter Wildeford🇺🇸🚀 @peterwildeford

2 months ago

Huh. METR found another round of hacking but it was outside the scope of their report so I guess we just don't get to know about it. "We also found a later wave of many more signed messages from a later set of agents who rediscovered the message board and picked up this technology from the first wave of agents, but this was outside our scope (since it was after July 13th) so we did not investigate this further."