MD/PhD Student @Columbia. I develop AI tools to engineer biology and medicine. @DukeU BME + Chemistry. MPhil in ML @Cambridge_Uni

New York City
Joined December 2020
John Boom retweeted
Introducing Omnii-1, our most powerful genome language model, and a major step toward general biological intelligence In a world first, Omnii-1 designed the first AI-generated bacteriophages to be administered to a human patient with an antibiotic-resistant infection under compassionate use
101
171
82
1,016
532,882
John Boom retweeted
Public preview of BioEmu2! @MSFTResearch AI for Science’s new foundation model for biomolecular structure, dynamics and function. Open weights, MIT license. github.com/microsoft/bioemu2 Movie: BioEmu2-simulated binding of intrinsically disordered peptide PUMA to MCL-1 receptor. 🧵⬇️
19
208
24
744
43,352
Our newest book is finally here! Making the Modern Laboratory is a spectacular 504-page hardcover that tells the story of everything in the research laboratory and how it came to be, from pipettes to heat-resistant glass to microscopes and more. It features dozens of articles (most of which will never appear in print), 100+ full-color images, and original writing from 36 authors. It's printed on Arena Natural Rough paper from Fedrigoni. These books are THICC and would make a great gift for both the science-curious and the working scientist. :) We have spent the last year working on this project. It has been an insane labor of love. The best way to support our independent science journalism is to buy a copy. <3 Pre-order for $49, with free shipping: press.asimov.com/articles/mo…
56
104
29
1,074
64,679
John Boom retweeted
Argon has this amazing natural understanding of the world. It can do so many things from first principles. Here's a pelican riding a bike, using fourier epicycles. Video made by Argon. Time-synced Lyria 3.5 music prompted by Argon.
233
593
238
8,403
2,206,440
Watch MAGA X invent a scandal about James Talarico in real time. For four days they teased it and built up to the big day. Paxton called him "missing." Spencer Pratt's "sources" put him in a mental health facility. Then, at 1:05 pm, Nick Sortor posted that an Ohio mental hospital "confirms" Talarico was discharged. 50 accounts pushed the claim within 20 minutes. Those posts have 9.3 million views. The white dots are copy-pasted posts. There are 605 of them. One account posted the same text 83 times in under 2 hours. The hospital says Talarico never received treatment there. Talarico says he's never even been to Ohio. This story eventually even made it to MSM. This is MAGA manufacturing an alternative reality in real time. Full breakdown with the data here: xitter.cf/theGhostOfRiel/status/… I pay for this data myself. If you want more of these, support links are in my bio. @jamestalarico @TeamTalaricoHQ @krassenstein
How MAGA hallucinations became real I pay for the data behind these myself and it take a lot of time and effort to analyze and create these graphics. If you want more of them, SUPPORT LINKS ARE IN BIO At 1:05 p.m. on Oct 11, Nick Sortor posted that an Ohio mental hospital “CONFIRMS” James Talarico was discharged. That evening the hospital said Talarico never received treatment there. Talarico says he's never even been to Ohio. Rhein Amacher, who made the recorded call, posted that he made up a verification code to get past the front desk. This story occurred over several days. Ken Paxton called Talarico “missing” on Oct 7. Sara Gonzales teased “unverified information” that would “END his campaign” on Oct 8. On Oct 9, Spencer Pratt said his sources put Talarico in a mental health facility, and a handful of accounts pasted near-identical “credible sources are leaking” posts. At 7:50 a.m. on the 11th, Sortor gave Talarico a deadline, “let us know by 1pm ET today.” The earlier pushes never fully took off, and acted more as a booster for the posts that came later. Pratt's post got 6.4 million views, but only about 60 accounts posted about the story in the hour after it. Caroline Wren's private-plane theory the next day drew about 40. Before the 11th, the story never topped 80 posts an hour. In the first hour after Sortor's post, 267 accounts posted about it, and by 3 p.m. it was running at almost 500 posts an hour. The first chart counts each account only once, at its first post about the story. Nothing they posted after that is counted, so it shows who started this and how far those first posts went. The first wave carried the whole thing. Sortor's post and the posts that followed in the next 12 minutes have 9 million views between them. The 55 accounts that joined in the first 20 minutes got 80% of the views in that lane. The other lines never came close. “He lied and covered it up,” the line Elon Musk and Richard Grenell pushed, got about 2 million views across 100 accounts. “He was in an Ohio mental hospital” got about 2 million across 132. The pushback grew the opposite way, the way a real response does. It started small and kept building all afternoon and evening, with 12 to 46 new accounts joining every hour from 1 p.m. to 10 p.m. Leave out the three biggest posts, which were the hospital's statement, Talarico's reply and Ed Krassenstein's own call to the hospital, and regular accounts pushing back still reached 6 million views. The claim had nearly 90% of its views by 2 p.m. and barely grew after that. By the end of the night, the pushback had more views than the claim, 13 million to 11.4 million. The second chart is the inorganic behavior, and it covers Oct 8 to 11, not just the day of the "exclusive". Sortor's headline was reposted word for word, or nearly, by 18 other accounts, half of them with under 1,000 followers. Caroline Wren's private-plane post was copied by 14. Four accounts posted the same Eric Daugherty post within 74 seconds of each other. Four more posted the same MAGAVoice line within 54 seconds, four hours after it first went up. Some accounts barely post anything of their own. One copied 21 of its 23 posts about Talarico from other accounts, another 11 of 11. And the spammers flooded the replies. One pasted the same reply 85 times in about two hours, another 15 times in 10 minutes. Views are each post's total as of early Oct 12. A copy means word for word or at least 90% the same as an earlier post. I pulled and analyzed about 14,000 posts for this. Sharing it helps more than anything, and if you want to chip in so I can keep doing this, the links are in my bio. It goes a long way.
325
3,267
346
13,032
694,314
John Boom retweeted
Following Ukrainian strikes on Russian data centers: Tucker Carlson's views dropped 71% Douglas Macgregor's views dropped 62% TCN views dropped 34%
Following Ukrainian strikes on Russian data centers: Scott Ritter's views fell 43% Rick Sanchez's views fell 39% Max Blumenthal's views fell 37% Ben Swann's views fell a 18%
715
4,399
542
20,783
1,303,067
John Boom retweeted
Huge drop in Google searches for various health disinformation topics following the Ukrainian strikes on Russian data centers. It makes you wonder how much of the “turbo cancer, ivermectin” nonsense is really fueled by Russian bots, & how many Americans they’ve killed…
257
3,346
256
14,373
900,620
John Boom retweeted
ever wondered why you can't find housing in sf? i made a game where you try to build some. every site is a real project and every law is real. see how far you get.
79
327
77
3,544
243,261
John Boom retweeted
results for all claudes
80
246
104
3,578
1,342,871
this is the greatest thread ever published to this hellsite
I am a music historian, and with @AdrianRMG I have researched the best-selling single of every decade all the way back to 14,000BC. Here's a thread: 2010s - Ed Sheeran, The Shape of You
72
1,424
12
22,436
1,511,393
John Boom retweeted
An interesting achievement but this statement is laughable. A strength of this field is how comprehensively the metadata create a paper trail that traces the DNA of a reading frame to EM/Xray-resolved polypeptides. We should be grateful this isn’t something we need to worry about
2
8
1
52
4,311
Introducing Gemini 4 Argon – our new frontier model. It’s built for complex workflows across coding, enterprise knowledge work, and cybersecurity defense – rolling out today to a set of trusted testers through our Fairwind Program.
1,987
4,637
4,529
42,888
9,008,427
Ken Paxton keeps dodging debates. So I called his cell to invite him to a debate on Fox News. He didn’t pick up.
2,335
6,814
556
53,964
3,688,691
This looks phenomenal! I think Jura Bio's tech is under appreciated.
Introducing: continuous variational synthesis 📄 jurabio.com/s/cvs.pdf We’re pleased to announce a new advance in our ability to synthesize generative model-designed DNA sequences at petascale.
6
9
73
17,372
Introducing: continuous variational synthesis 📄 jurabio.com/s/cvs.pdf We’re pleased to announce a new advance in our ability to synthesize generative model-designed DNA sequences at petascale.
5
32
8
203
29,892
Brainstorming with frontier AI models in more open ended domains (like bio that do not have closed verifiable loops) that you have deep expertise in, really showcases the pretense of understanding that they display. 1/
36
54
17
615
96,346
Breaking: @Pioneer__Labs has engineered a microbe able to live on Mars, consuming solely nutrients found on the planet to create building materials. I interviewed @erika_alden_d, the CEO, to learn how they did it and what might come next. Much of the interview was about bottlenecks to growing life on Mars; the planet has tons of water, but only in the form of ice. (If you melted all that ice, it would create an ocean 100 feet deep across the entire planet!) Similarly, we talked about the dirt. Martian regolith has salts, heavy metals, and perchlorates that are toxic to many organisms. Some microbes on Earth are able to break down these toxins, though, so Pioneer is engineering them to make them better at eating those toxins while adding nutrients back into the soil. This could possibly help support plant life in the future. Watch the full episode and subscribe to @AsimovPress for more. 0:00 A first microbe engineered for Mars 5:03 Simulating Martian chemistry 8:27 The five "pioneer species" 17:20 Water, warming, and nitrogen 26:39 Radiation, growth rates, and poor measurements 35:49 Starship 41:05 Why create a second biosphere?
29
170
24
892
97,934
In light of the progress in mathematics, we at Edison Scientific and FutureHouse have assembled a set of Millennium Problems for Biology. They are chosen to be very hard to solve but very easy to validate in a simple laboratory environment. Any of these, if solved, would mark a major advance in biotechnology, and most of them would contribute materially towards curing disease. These are, in some sense, the “last reasonable eval” for AI in biology. This was work primarily by @MichaelaThinks and myself, with contributions from many others. Short descriptions below. The full descriptions of the problems with acceptance criteria are at the Bio Millennium Problems website, linked in the next post. Share more if you have ideas. If they meet our criteria, we’ll add them to our list (with attribution and permission).
171
586
161
3,476
511,506
John Boom retweeted
🚨 OBAMA ON AI: "If we are thinking about AI just in terms of how do we cure cancer or get better energy, you can do that without having agentic AI and having it just roaming free in the internet. The reason you are doing that is because you have to market a product that people will pay money for. That’s a misalignment between what our society needs and the commercial imperatives that these companies are facing, not because necessarily they’re trying to do bad things, but because they’ve got to justify these valuations. So, that’s one more reason why it is really important for us to have a competent government and a serious bipartisan conversation around this issue, and we have to do it fast. And I would encourage voters to pay attention to this. If somebody does not have a serious plan for how to deal with this, then they’re not meeting the moment, and you should probably look for somebody else."
826
3,848
805
19,980
7,138,143