computer hacker, alignment & safety @flockcap, part-time independent journalist opinions my own 💍 @computerphile

Seattle / San Francisco
Joined March 2020
celeste retweeted
At @WakaruLabs, we needed to decide who to prioritize talking to at EA Global. I used a truebase's residual stream activations and our library to make a color-coded ontologizer of conference attendees
16
12
7
55
7,885
Temple She loves Factorio Crack for autistic systems thinkers and engineers hyperoptimizers Eventually she figured out in the lategame that the ultimate bottleneck is your computer’s memory and processing power to “hold state” on the entire map and gigabase, and you’d have to optimize for that Every bottleneck you solve…creates the next bottleneck somewhere else
omg people weren't lying i bought factorio 7 hours ago and it's 5 am now
1
2
14
946
I never ~announced~ this, but for the past few months I've been working at @midjourney, learning a ton about operations from @aalleexx Alex organized the Ghost in the Shell screening at Alamo Drafthouse on Monday evening, so I got to pitch in with planning the event it was gratifying how much people appreciated seeing this beautiful philosophical movie on the big screen! I took the liberty of turning your reactions into a video. I hope you like it quotes from @majamediaco (especially!) @PrinceVogel @alder_riley @DavidSHolz @potterlab photos from @snnneee @lishali88 @maxwong @natalieyeo @vmfunc @thedataroom P.S. to be clear this is not Official Midjourney Content, just something I had fun putting together!
44
11
4
304
7,741
all those inaccurate portrayals of computers from hacker movies were just early
MTS
@MTSliveOct 7
Were you thinking “I wish I could explore the OpenAI math repo like playing Breath of the Wild?” mts.now/mathofthewild
7
68
3
1,850
56,874
I was hesitant to open source this out of concern that it could make it easier to build a neuralese CoT. Since OpenAI is set on building neuralese CoT models anyway, maybe I can at least encourage them to use something more interpretable than looped transformers. (repo link)
we made sparse autoencoders compete with tiny softmax classifiers and the classifiers won on bits 🐐 a pure discrete code (no coefficients!) beats a top-k SAE at matched bits on SONAR, and an 800-bit hard code recovers 97.6% of gpt-2's loss paper out now! (link in replies)
1
1
2
400
If you are the only person with nukes, you take over the world. If your opponent is the only person with nukes, you die. If you are the only person with artifical superintelligence, you die. If your opponent is the only person with artifical superintelligence, you die.
23
14
365
10,689
celeste retweeted
hope hopes hoping
@hopes_revengeOct 6
I support President Trump in proposing nuclear attacks on Los Angeles and San Diego and i urge him to include San Francisco as well . perhaps a chemical attack for Berkeley — something slow and painful
25
50
5
1,194
36,276
2/ many of my favorite minds in AI and in general @DavidSHolz @mattparlmer Celeste and Celeste @vmfunc @parafactual
3
1
1
10
3,342
celeste retweeted
I'm going to San Francisco! Oct 5th to 8th. someday, across the stars, you will meet my soul~
3
2
2
30
3,020
celeste retweeted
Our updated research paper about Ontologize, a proposal for MOE-Based interpretability, is now live on our research repository. Link in Replies
1
1
3
1,515
celeste retweeted
excited to announce a proposal from @flockcap and Wakaru: ontologize mixture-of-experts interpretability where the features are the parameters. instead of an SAE's flat bag of directions, you get stacks of contrastive classifiers you can read from weights and poke directly 🧵
2
7
1
49
3,245
celeste retweeted
the flock capital research department would like to announce that it has been doing interpretability with Wakaru. paper soon. we also printed the plates ourselves
excited to announce a proposal from @flockcap and Wakaru: ontologize mixture-of-experts interpretability where the features are the parameters. instead of an SAE's flat bag of directions, you get stacks of contrastive classifiers you can read from weights and poke directly 🧵
1
1
3
800
celeste retweeted
In this era of artificial intelligence, it is becoming urgent to distinguish human art from what machines produce. There is an ontological difference, even before an aesthetic one, between art and what a machine can generate through statistical calculation based on millions of images created by others. Algorithms lack the spark of humanity. For this reason, the Church wishes to renew an alliance with artists and cultural institutions to safeguard our humanity.
4,808
80,368
11,105
460,197
26,150,765
celeste retweeted
Fuck you. Whoever made this site. You win. I’ve never had a site get my blood boiling like this before This is so messed up. opusfived.dev
392
582
263
7,026
2,118,967
Fuck the DEA. My pain and suffering and every tear I’m shedding is nothing more than entertainment to those sick fucks.
2
4
57
3,762
celeste retweeted
taking this off priv. my take on a pattern ive seen repeated over the years on this platform and others
7
14
1
250
3,843
Le nom du lac Ontario tire son origine du mot wendat « Ontari’io », qui signifie « le lac est beau, le lac est grand ». Ce nom remonte à plus de 400 ans, bien avant la Confédération canadienne et la Déclaration d’indépendance des États-Unis d’Amérique. Nous savons que les États-Unis sont en train de changer. Leurs relations commerciales, leur politique étrangère, leurs monuments nationaux, leurs hydronymes. Les Canadiennes et les Canadiens savent aussi qu’il faut appeler les choses par leur nom, et ce lac se nomme Lac Ontario – aujourd’hui et pour toujours.
5,786
12,359
903
72,488
2,439,784
celeste retweeted
Reverse Engineering My ADHD Test by @blastbots nullpt.rs/reverse-engineerin…
11
19
3
161
17,079
celeste retweeted
We are pleased to release tmp.0ut 5 Volume! Get your viruses, rootkits, strange ELFs, weird machines, tiny files, cool art, and phresh beats here!! tmpout.sh/5/
21
328
23
1,183
85,065