←
noah1,214 posts
noah avatar

noah

@immunity
◷ Joined July 2010▧ 252 Photos and videos
noah avatar
noah@immunity·Feb 23

Please tell those close to you that you love them while you still can, it becomes heart wrenching when you no longer can but still yearn to do so.

noah avatar
noah@immunity·Feb 23

Years went by where she was the only one to believe in me, I achieved my professional goals in time for her to see the path I was on, I know she was proud so I’m going to continue down it.

noah avatar
noah@immunity·Feb 23

I scaled back a lot of what I was doing in the interim and will likely not use this account much going forward.

noah avatar
noah@immunity·Feb 23

The news devastated me and derailed my plans for the rest of the year. It made me seriously depressed, it was hard to keep going every day

noah avatar
noah@immunity·Feb 23

I have been gone a while When I got home from SF last July I found out my Mother was diagnosed with terminal stomach cancer, this month I lost her.

noah avatar
noah@immunity·2 Jul 2025

I am going to be in SF till the 13th, if you are interested in talking to me please reach out, my goal for this trip is to meet as many people in ml research and engineering as possible. I have just updated my personal website (noah dot jp dot net) with the relevant information!

Post attachmentPost attachment
noah@immunity2 Jul 2025

I did it. I reached Highway 101 leading into downtown San Francisco with all the AI SaaS ads. This must be what Hannibal felt like after he cleared the Alpine Pass

noah avatar
noah@immunity·2 Jul 2025

I did it. I reached Highway 101 leading into downtown San Francisco with all the AI SaaS ads. This must be what Hannibal felt like after he cleared the Alpine Pass

Constantin Venhoff avatar
⟳ noah retweeted
Constantin Venhoff@cvenhoff00·20 Jun 2025

🔍 New paper: How do vision-language models actually align visual- and language representations? We used sparse autoencoders to peek inside VLMs and found something surprising about when and where cross-modal alignment happens! Presented at XAI4CV Workshop @ CVPR 🧵 (1/6)

Post attachment
Shangshang Wang avatar
⟳ noah retweeted
Shangshang Wang@UpupWang·12 Jun 2025

Sparse autoencoders (SAEs) can be used to elicit strong reasoning abilities with remarkable efficiency. Using only 1 hour of training at $2 cost without any reasoning traces, we find a way to train 1.5B models via SAEs to score 43.33% Pass@1 on AIME24 and 90% Pass@1 on AMC23.

Post attachment
Victor Veitch 🔸 avatar
⟳ noah retweeted
Victor Veitch 🔸@victorveitch·6 Jun 2025

In particular, I think the current wave of SAE skepticism is about as irrational as the wave of SAE hype that preceded it. It is wholly plausible that there are a set of improvements that will lead to massive improvements. Just, those improvements won't be found by throwing spaghetti at the wall. This is a situation where a deeper, more careful, understanding of the underlying structures is really necessary.

Ekdeep Singh Lubana avatar
⟳ noah retweeted
Ekdeep Singh Lubana@EkdeepL·6 Jun 2025

🚨 New paper alert! Linear representation hypothesis (LRH) argues concepts are encoded as **sparse sum of orthogonal directions**, motivating interpretability tools like SAEs. But what if some concepts don’t fit that mold? Would SAEs capture them? 🤔 1/11

Thankful Brian Graham 🦬🦃 avatar
⟳ noah retweeted
Thankful Brian Graham 🦬🦃@iroasmas·28 May 2025

am i sure the death star is going down? look at my quant. look at him! you notice anything different about him? look at his eyes. i’ll give you a hint—his name’s a fucking number!! he doesn’t even speak english—it’s all beep-boop shit!! yeah, i’m sure.

Post attachment
Goodfire avatar
⟳ noah retweeted
Goodfire@GoodfireAI·27 May 2025

We created a canvas that plugs into an image model’s brain. You can use it to generate images in real-time by painting with the latent concepts the model has learned. Try out Paint with Ember for yourself 👇

0:22
0:30
0:29
0:19