Interesting talk on intelligence, computation, and life. Relates to assembly theory, cellular automata, evolution, and emergence. youtu.be/M2iX6HQOoLg?si=D3lU… via @YouTube
Lisa Watts retweeted
#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…
Lisa Watts retweeted
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
@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
260
Lisa Watts retweeted
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…
Lisa Watts retweeted
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: 🧵👇🏾
Lisa Watts retweeted
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…
Lisa Watts retweeted
Nature research paper: Parallel molecular data storage by printing epigenetic bits on DNA go.nature.com/3Ujwvv0
The sun's corona is weirdly hot, and Parker Solar Probe rules out one explanation phys.org/news/2024-07-sun-co…
Lisa Watts retweeted
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:
Star jelly - Weird. en.wikipedia.org/wiki/Star_j…
How to grow fresh air | Kamal Meattle youtu.be/gmn7tjSNyAA via @YouTube
I'm voting for @macrocosmcorp to embed all repositories on Github and open-source the weights. alex.macrocosm.so/download
Lisa Watts retweeted
You can download the Arxiv embeddings (titles and abstracts, 6gb and 8gb respectively) at the link below.
There's a lot of datasets to choose from, so we need your help to figure out what to work on next. Let us know by voting!
Download or vote here:
alex.macrocosm.so/
Well done, and good luck!



















