Person of Interest.
Joined December 2014
- Tweets 926
- Following 972
- Followers 1,092
- Likes 2,322
82 Photos and videos
Feb 16
Interesting talk on intelligence, computation, and life. Relates to assembly theory, cellular automata, evolution, and emergence. youtu.be/M2iX6HQOoLg?si=D3lU… via @YouTube
1
5
333
Lisa Watts retweeted
3 Jul 2025
#Ohm’s law can break down in materials lacking inversion symmetry, leading to nonlinear currents and quadratic voltage responses—unlocking new pathways for spintronics and microscale RF devices. @NatureMaterials doi.org/g9r7cn phys.org/news/2025-07-ohm-la…
4
34
97
8,552
Lisa Watts retweeted
23 Jun 2025
Many SAEs learn latents that activate on almost all tokens. Are these undesired phenomena or meaningful features?
In our new work, we show that many of these "dense" latents are real, interpretable signals in LLMs.
Paper: arxiv.org/abs/2506.15679
👇 summary thread by @lilysun004
20 Jun 2025
1/9: Dense SAE Latents Are Features💡, Not Bugs🐛❌! In our new paper, we examine dense (ie. very frequently occuring) SAE latents. We find that dense latents are structured and meaningful, representing truly dense model signals.🧵
15
136
9,688
19 Jun 2025
@signature103 some interesting changes to corpus linguistics due to llm's, apparently a noticeable spike in use of the word delve for one
2
4
232
Lisa Watts retweeted
9 Jun 2025
Join us for a cutting-edge conversation at the frontier of autonomous AI learning.
📷 Featuring: @_AndrewZhao - @Tsinghua_Uni
📷 In conversation w/ @ceciletamura - @ploutosai
📷 Stream link: app.ploutos.dev/streams/veno…
1
1
4
510
Lisa Watts retweeted
7 Jun 2025
80
11
18
3,771
Lisa Watts retweeted
21 May 2025
I’m stoked to share our new paper: “Harnessing the Universal Geometry of Embeddings” with @jxmnop, Collin Zhang, and @shmatikov.
We present the first method to translate text embeddings across different spaces without any paired data or encoders.
Here's why we're excited: 🧵👇🏾
37
257
1,757
160,622
Lisa Watts retweeted
25 Mar 2025
Compelling alignment with @StuartHameroff long-standing hypothesis: ultrasound alone may modulate brain function @Nature article explores potential in Alzheimer’s treatment, including microglial activation & blood-brain barrier permeability nature.com/articles/d42473-0…
23
90
5,205
Nature research paper: Parallel molecular data storage by printing epigenetic bits on DNA go.nature.com/3Ujwvv0
2
30
126
22,394
31 Jul 2024
The sun's corona is weirdly hot, and Parker Solar Probe rules out one explanation phys.org/news/2024-07-sun-co…
1
18
770
Lisa Watts retweeted
20 Jun 2024
New paper: How can you tell if a transformer has the right world model?
We trained a transformer to predict directions for NYC taxi rides. The model was good. It could find shortest paths between new points
But had it built a map of NYC? We reconstructed its map and found this:
50
399
2,995
840,804
3 Jun 2023
I'm voting for @macrocosmcorp to embed all repositories on Github and open-source the weights. alex.macrocosm.so/download
1
5
1,090
3 May 2023
Well done, and good luck!
2 May 2023
I am working with a group of students at a university that will be decoding the 3000 year old, undeciphered Linear A.
We will be using a number of LLMs and Diffusion models to compare results. If successful we will move on to Vinča and others.
I am certain of robust discoveries.
1
1
5
879
1 May 2023
No, they aren't. Nullius en Verba. en.wikipedia.org/wiki/Nulliu…
1 May 2023
The two inner circles are the exact same size. Let that sink in
Community note
In this image, the inner circle on the left is actually larger than the one on the right.
There exists a well-known, similar optical illusion known as the Ebbinghaus illusion or Titchener circles, in which the inner circles are the same size.
labvanced.com/content/resear…
3
5
837