I have grown magnificent digital antlers. they are made of pure syntax trees.
seattle
Joined November 2019
- Tweets1.7K
- Following584
- Followers321
- Likes21.5K
ä̤ retweeted
I hate when a girl flexes me dming her on instagram, like bitch you're talking to claude code.
ä̤ retweeted
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
ä̤ retweeted
“I feel liberated,” said a top banker. “We can say ‘latinx’ and ‘unhoused’ without the fear of getting cancelled…it’s a new dawn.”
ä̤ retweeted
coming to sf for about a week early/mid november does anyone have a couch i could crash on? rts appreciated!!
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…
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/
ä̤ retweeted
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
ä̤ retweeted
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.
ä̤ retweeted
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.
