←
Quinoah 🔍⏸️17,533 posts
Quinoah 🔍⏸️ avatar

Quinoah 🔍⏸️

@NoahTopper

yudkowsky's bulldog | AI safety grantmaking @coeff_giving (opinions my own)

◷ Joined August 2012▧ 1,888 Photos and videos
Quinoah 🔍⏸️ avatar
Quinoah 🔍⏸️@NoahTopper·Nov 16

Immortal elf step father be like

My step dad just said "Constantinople, or Istanbul, or whatever they're calling it these days. They change it all the time, seems like", and then shrugged it off when I told him the last time they changed its name was like five hundred years ago

Andy Masley avatar
⟳ Quinoah 🔍⏸️ retweeted
Andy Masley@AndyMasley·Nov 3

Our first timeless decision theory President

Trump: "I've kept every single promise I made, except far more. I've actually kept far more promises than I made."

0:14
Quinoah 🔍⏸️ avatar
Quinoah 🔍⏸️@NoahTopper·Oct 28

I think there is much bad in everyone dying

Post attachment

I think "AI kills everyone" takes up too much space in our brain, and probably distorts our actions away from trying to keep AI safe. It's a weird corner solution, where there's not much bad in everyone dying. It's the messy catastrophes which are probably much more likely.

Ryan Moulton avatar
⟳ Quinoah 🔍⏸️ retweeted
Ryan Moulton@moultano·Oct 15

XKCD: I wrote xkcd.com/221/ "Random Number" as a cautionary tale. Tech Company: At long last, we have created the Random Number from classic web comic Don't Create The Random Number.

This is the least surprising graph in the world if you understand how gradient descent works.

Post attachment
tomato girl avatar
⟳ Quinoah 🔍⏸️ retweeted
tomato girl@visceraldream·Oct 22

Just Saw Everything. My takeaway is that I want to have sex with Nathan Fielder

Marc Porter Magee 🎓 avatar
⟳ Quinoah 🔍⏸️ retweeted
Marc Porter Magee 🎓@marcportermagee·Oct 19

Early Nathan Fielder. He got to interview his boss on the air and made it as awkward as possible.

2:05
Quinoah 🔍⏸️ avatar
Quinoah 🔍⏸️@NoahTopper·Oct 18

huge result: santa actually lives at the *south* pole

Post attachment

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/

Quinoah 🔍⏸️ avatar
Quinoah 🔍⏸️@NoahTopper·Oct 18

I do actually think in the longterm future it would be good for humans to be the ones making art and doing mathematics

hope hopes hoping avatar
⟳ Quinoah 🔍⏸️ retweeted
hope hopes hoping@hopes_revenge·Oct 17

the elizabeth holmes movie inspired me to worship my evil autistic wife even harder

Quinoah 🔍⏸️ avatar
Quinoah 🔍⏸️@NoahTopper·Oct 17

I binged a bunch of Nathan Fielder in preparation for the documentary and he has quickly become one of my comedy heroes. How does his mind work like that