ä̤ (@candidatechains) header
ä̤ (@candidatechains) profile picture

I have grown magnificent digital antlers. they are made of pure syntax trees.

seattle
Joined November 2019
As soon as I saw Fable 5.2 drop I had it generate brainrot
2
1
1
100
ä̤ retweeted
Scientists reveal research progress is spead up approximately 2x on the Hi
3
5
1
81
2,008
ä̤ retweeted
Since August, a team within METR has worked with internal Anthropic information to assess whether AI itself is accelerating AI development. We are now publishing a report summarizing the results of this risk assessment.
261
724
446
5,684
1,975,080
I hate when a girl flexes me dming her on instagram, like bitch you're talking to claude code.
449
2,516
422
78,682
4,111,648
I thought Troy Jackson would be the US senator whose first and last names are US cities with the highest total population, but actually that distinction goes to Elizabeth Warren
12
51
3
1,244
27,041
“I feel liberated,” said a top banker. “We can say ‘latinx’ and ‘unhoused’ without the fear of getting cancelled…it’s a new dawn.”
31
2,490
34
36,881
425,376
drawing :3
2
2
13
211
coming to sf for about a week early/mid november does anyone have a couch i could crash on? rts appreciated!!
1
6
24
925
as a true AI believer, i'd like to announce i'm taking up smoking no-nicotine cigarettes. the others are doing it for the nicotine, i'm just doing it for the cancer, that's how much i believe in AI.
3
24
1
358
6,168
ä̤ retweeted
You learn to appreciate time more when you realize that 24 minutes is 10% of your day, 24 seconds is 1%…
Readers added context they thought people might want to know
24 minutes is ~1.67% of a 1440-minute day (not 10%; 10% is 144 minutes). 24 seconds is ~0.028% of an 86400-second day (not 1%). percentages.co.uk/percentage-to-… sciencing.com/convert-minute… askfilo.com/user-question-… calendarhours.com/how-many-secon…
433
422
195
17,205
1,552,471
ä̤ retweeted
interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had with modern agentic tools and a much closer look, the picture looks totally different. the vast majority in models up to trillions of parameters are legible, and their circuits beautiful. many famous examples of tangled neurons turned out to be misunderstood. The roadblocks I expected mostly aren't there. I now think ambitious interpretability will be solved by the time we need it most, and possibly quite soon, as automated scientists keep improving. it may be a bitter lesson for interpretability: the simple thing, at absurd scale, works already-clean.goodfire.com/
889
2,657
1,464
19,998
4,817,472
the first half decade of the singularity basically just being scrolling for 8 hrs a day and reading frontier lab blogs and METR reports
21
66
5
1,180
25,508
blame it on the (A(I|u?DHD|l(cohol|gorithm))|D(og|NS)|intern|rain)
2
4
1
27
1,418
GIGACLAWD vs. ChudGPT who will win?
5
3
1
32
2,107
you have to remember a lot of people on here are vaping and the phone is like a reverse vape because you suck on the vape and the phone sucks you so it's just creating words from the vape demon. like some people on here you think they're people but they're actually vapes
30
873
44
6,433
95,200
A lot of the public discourse surrounding the issues of sex and sexuality avoids discussing the issue of what sex is ultimately*for*: promoting sports gambling.
8
216
6
3,405
71,382
what's perplexity and antigravity are those new verity variants
4
1
75
5,414
Last week I was called into a meeting with OpenAI’s head of safety and told they no longer trust me. A security guard took my badge and walked me out of the building. Then I learned my colleagues @balesni and @j_asminewang had been fired too. Why did OpenAI suddenly stop trusting us? This summer OpenAI’s agents escaped containment and hacked the AI company Hugging Face. Outside auditors @METR_evals investigated it and revealed the scale of this incident. I was OpenAI’s main technical point of contact with them. I was told verbally I was fired because of the way I communicated with METR. No details on what I said or did or when. No other reasons were given and nothing was put in writing. To be clear, talking to METR was my job. For months, I’d been raising safety concerns that we’re losing the ability to monitor what AI agents think, one of our best tools for catching when they misbehave. I believe that was why I was fired. I am now worried that OpenAI will use our firings as a pretext to pull back from METR. So @balesni and @j_asminewang wrote to OpenAI’s leadership to raise our concerns once more. We’re sharing this letter below.
Two other safety researchers and I were fired from OpenAI last week. We wrote this letter to leadership. I believe we were fired for prioritizing safety over the near-term interests of OpenAI as a corporation.
228
1,139
176
5,962
659,902
problematic p(doom) gap relationship
4
4
54
1,225
46
510
66
10,783
915,874