252 Photos and videos
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!
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
2
2
27
6,210
noah retweeted
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)
10
41
298
68,995
noah retweeted
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.
10
55
499
72,341
noah retweeted
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.
1
31
2,208
noah retweeted
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
5
60
379
39,117
hey its me :)
1 Jun 2025
Emergent Ventures winners, 43rd cohort: marginalrevolution.com/margi…
6
20
1,461
noah retweeted
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.
26
338
5,972
246,663
noah retweeted
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 👇
39
95
917
179,692
A lot of alpha in this graph
remember “Large Language Models are Zero-Shot Reasoners” as well?
I love it when a plan comes together
27 May 2025
🚀 Excited to share the most inspiring work I’ve been part of this year:
"Learning to Reason without External Rewards"
TL;DR: We show that LLMs can learn complex reasoning without access to ground-truth answers, simply by optimizing their own internal sense of confidence. 1/n
1
1
3
1,012
noah retweeted
27 May 2025
🚀 Excited to share the most inspiring work I’ve been part of this year:
"Learning to Reason without External Rewards"
TL;DR: We show that LLMs can learn complex reasoning without access to ground-truth answers, simply by optimizing their own internal sense of confidence. 1/n
86
504
3,463
575,158
noah retweeted
23 May 2025
The more I look into the system card, the more I see over and over 'oh Anthropic is actually noticing things and telling us where everyone else wouldn't even know this was happening or if they did they wouldn't tell us.'
23 May 2025
Humans can be trained just like AIs. Stop giving Anthropic shit for reporting their interesting observations unless you never want to hear any interesting observations from AI companies ever again.
9
72
1,677
306,278