Excellent stuff from Greta! 👌🇵🇸🇵🇸🇵🇸
06.10.2025 17:09 — 👍 196 🔁 82 💬 8 📌 6@deathstarrobot.bsky.social
Author of original theories in Neuroscience, Physics, and Artificial Intelligence. https://tinyurl.com/3yucdp8c
Excellent stuff from Greta! 👌🇵🇸🇵🇸🇵🇸
06.10.2025 17:09 — 👍 196 🔁 82 💬 8 📌 6This is a category error for me, not for you? Apples vs Oranges?
06.10.2025 18:14 — 👍 0 🔁 0 💬 0 📌 0This evening, President Trump is ordering 400 members of the Texas National Guard for deployments to Illinois, Oregon, and other locations within the United States. No officials from the federal government called me directly to discuss or coordinate.
06.10.2025 01:44 — 👍 13515 🔁 4314 💬 708 📌 401This is a breathtaking abuse of the law and power by the President of the United States.
America is on the brink of martial law.
Do not be silent.
We are alarmed by reports that Germany is on the verge of a catastrophic about-face, reversing its longstanding and principled opposition to the EU’s Chat Control proposal which, if passed, could spell the end of the right to privacy in Europe. signal.org/blog/pdfs/ge...
03.10.2025 16:14 — 👍 3921 🔁 2426 💬 40 📌 146📣 Germany's close to reversing its opposition to mass surveillance & private message scanning, & backing the Chat Control bill. This could end private comms-& Signal-in the EU.
Time's short and they're counting on obscurity: please let German politicians know how horrifying their reversal would be.
This is an EU proposed policy with the benign-sounding name "Child Sexual Abuse Regulation" which proposes to screen private online communications using sketchy image-scanning algorithms. It is technically unworkable, and would be a privacy catastrophe, especially for those in authoritarian states
06.10.2025 08:42 — 👍 155 🔁 68 💬 4 📌 1I am preparing to defend myself on Oct 8th at my local swim club. They have wrongfully suspended me. #SERC You can read about it here. www.svgn.io/p/open-lette... The South End Rowing Club.
06.10.2025 06:33 — 👍 0 🔁 0 💬 0 📌 0People are running stats on LLM-generated participants and think they’re being social scientists when in fact they’re technically just playing a very strange video game. This is like saying you’re doing math research because you’re playing sudoku.
www.science.org/content/arti...
Paper title "The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?" with the paper's graphical abstract showing how more powerful alignment maps between a DNN and an algorithm allow more complex features to be found and more "accurate" abstractions.
Mechanistic interpretability often relies on *interventions* to study how DNNs work. Are these interventions enough to guarantee the features we find are not spurious? No!⚠️ In our new paper, we show many mech int methods implicitly rely on the linear representation hypothesis🧵
14.07.2025 12:15 — 👍 62 🔁 12 💬 1 📌 1Yesterday the Royal Society held a series of panels & keynotes in celebration of the 75th anniversary of the Turing Test. The unanimous critical takes on AGI, big tech's power concentration & the call for urgent action left me w hope things might be turning
Watch here m.youtube.com/live/GmnBTCK...
See, the thing is, Singal did violate the TOS, unambiguously. An then Bluesky changed it to accommodate him. You know this to be the case; you were there just as much as I was. So you're telling a lie. And you know it to be a lie. And that kind of makes you look like a shithead. I'm just saying.
02.10.2025 13:10 — 👍 1743 🔁 506 💬 8 📌 3Equivalent Concepts (after translation appear first in Micah Blumberg’s work and later MIT Scientist Earl K. Miller’s Work, different concepts across multiple papers, without citation.
www.svgn.io/p/conceptual...
The stark contrast between what is in the training (protecting against foreign influence, merit-based competition, freedom of inquiry, non-bias) and how the administration is acting is stunning. I feel like i've entered fucking bizzaro world
29.09.2025 19:38 — 👍 20 🔁 5 💬 2 📌 0U.S. Border Patrol agents tried and failed to detain a man in downtown Chicago (via Christopher Sweat)
29.09.2025 11:44 — 👍 6361 🔁 1210 💬 766 📌 375Who said "traffic congestion" ? If your argument is the brain is complex, and that my argument and or your brother's argument is reductionist, that's besides the point that he's publishing a point that is equivalent to the point that I published first years prior, and that's just the first thing.
29.09.2025 21:15 — 👍 0 🔁 0 💬 0 📌 0The equivalences are proven with category theory and pi calculus, it's irrefutable, and the dates confirm my work has priority. Now you know something about your brother.
29.09.2025 21:02 — 👍 0 🔁 0 💬 1 📌 0David Cox FYI: Equivalent Concepts (after translation appear first in Micah Blumberg’s work and later MIT Scientist Earl K. Miller’s Work, different concepts across multiple papers, without citation. www.svgn.io/p/conceptual...
29.09.2025 21:01 — 👍 0 🔁 0 💬 0 📌 0Mackenzie Weygandt Mathis FYI: Equivalent Concepts (after translation appear first in Micah Blumberg’s work and later MIT Scientist Earl K. Miller’s Work, different concepts across multiple papers, without citation. www.svgn.io/p/conceptual...
29.09.2025 21:00 — 👍 0 🔁 0 💬 0 📌 0Julie Haas FYI: Equivalent Concepts (after translation appear first in Micah Blumberg’s work and later MIT Scientist Earl K. Miller’s Work, different concepts across multiple papers, without citation. www.svgn.io/p/conceptual...
29.09.2025 21:00 — 👍 0 🔁 0 💬 0 📌 0CLaE FYI: Equivalent Concepts (after translation appear first in Micah Blumberg’s work and later MIT Scientist Earl K. Miller’s Work, different concepts across multiple papers, without citation. www.svgn.io/p/conceptual...
29.09.2025 20:59 — 👍 0 🔁 0 💬 0 📌 0Jeni Kubota FYI: Equivalent Concepts (after translation appear first in Micah Blumberg’s work and later MIT Scientist Earl K. Miller’s Work, different concepts across multiple papers, without citation. www.svgn.io/p/conceptual...
29.09.2025 20:59 — 👍 0 🔁 0 💬 0 📌 0Eli Friedman FYI: Equivalent Concepts (after translation appear first in Micah Blumberg’s work and later MIT Scientist Earl K. Miller’s Work, different concepts across multiple papers, without citation. www.svgn.io/p/conceptual...
29.09.2025 20:58 — 👍 0 🔁 0 💬 0 📌 0Aidan Horner FYI: Equivalent Concepts (after translation appear first in Micah Blumberg’s work and later MIT Scientist Earl K. Miller’s Work, different concepts across multiple papers, without citation. www.svgn.io/p/conceptual...
29.09.2025 20:58 — 👍 0 🔁 0 💬 0 📌 0Jan Hartung FYI: Equivalent Concepts (after translation appear first in Micah Blumberg’s work and later MIT Scientist Earl K. Miller’s Work, different concepts across multiple papers, without citation. www.svgn.io/p/conceptual...
29.09.2025 20:57 — 👍 0 🔁 0 💬 0 📌 0Theresa Desrochers, Ph.D. FYI: Equivalent Concepts (after translation appear first in Micah Blumberg’s work and later MIT Scientist Earl K. Miller’s Work, different concepts across multiple papers, without citation. www.svgn.io/p/conceptual...
29.09.2025 20:57 — 👍 0 🔁 0 💬 0 📌 0Ya'el Courtney, PhD FYI: Equivalent Concepts (after translation appear first in Micah Blumberg’s work and later MIT Scientist Earl K. Miller’s Work, different concepts across multiple papers, without citation. www.svgn.io/p/conceptual...
29.09.2025 20:56 — 👍 0 🔁 0 💬 0 📌 0Ellen Kuwana, MS FYI: Equivalent Concepts (after translation appear first in Micah Blumberg’s work and later MIT Scientist Earl K. Miller’s Work, different concepts across multiple papers, without citation. www.svgn.io/p/conceptual...
29.09.2025 20:55 — 👍 0 🔁 0 💬 0 📌 0