Notes from Fable 5.2 contact prediction analysis:
- Results were NOT reproducible from run to run with the same simple prompt I shared last night.
- Within the session where it worked, I asked it 2 provide a detailed prompt of how it get there:
gist.github.com/sokrypton/3b…
(1/2)
I promised more on TMol in the RFD4-Proteina thread. Now with the paper on arxiv here we go! 🧵
Rosetta-style all-atom energies, GPU batching, and gradients in PyTorch. A way to put molecular energetics directly into your model, combining deep learning with physics. 1/n
“Wet-lab validated.” AI binder design papers keep reporting impressive hit rates. But does it bind in a second lab?
One independent retest: only 29/107 published AI-designed nanobodies showed binding—and 6 of those had high aggregation.
Germinal stands out for the wrong reason: just 1 of 12 published binders showed detectable binding on retest—a result that warrants an explanation.
How much trust should we put in headline hit rates?
Read more on my blog 👇
smiles724.github.io/blog/ai-…
Given Claude Fable 5.2 can predict protein sequence, I was curious if it can predict structure.
I gave it a relatively simple prompt: "predict contacts, 2ndary struct, use dynamic prog. and linear alg. to predict structure"
It was able to predict fold of ubiquitin correctly 🤯
Put the same PhD student in a small lab and in a powerhouse lab at Stanford, MIT or the Broad Institute, and you are basically running two different careers.
In a top lab, money is rarely the first constraint.
You have better equipment, better datasets, stronger collaborators, experienced postdocs, grant support, and people around you who already know exactly what a Nature, Science, Cell, NeurIPS or CVPR paper is supposed to look like.
Look at the Broad Institute. It has entire genomics, proteomics, imaging and genetic-perturbation platforms built to support projects that a normal university lab could never run alone.
Feng Zhang isn’t just “a very smart professor” — he sits at the intersection of MIT, Broad, McGovern and HHMI. That ecosystem matters.
Same in AI. Fei-Fei Li didn’t build ImageNet in isolation in somebody’s basement.
She was operating inside the Stanford AI ecosystem, surrounded by elite students, collaborators and an institution built to turn ambitious ideas into major projects.
MIT CSAIL is another absurd example: around 1,800 researchers and a research budget of roughly $65 million a year.
A PhD student entering that environment is not starting from the same line as someone in a five-person lab fighting for GPU hours and begging for travel money.
Of course talent still matters. Hard work still matters.
But academia loves pretending everyone is competing on the same track.
They’re not.
Some students spend three years figuring out how the game works.
Others enter a lab where the game manual, the coaches, the equipment and half the winning team are already sitting in the room.
If you seriously want an academic career, choosing the lab may be one of the highest-leverage decisions you ever make.
Just to think about what this implies - an inverse folding model like ProteinMPNN achieves a perplexity of ~4-5 on truly held out proteins when *given the structure*.
Claude is getting a perplexity of 2.2! What does this mean?
The most surprising part for me is that Fable 5.2 has massive gains over protein language model, for next amino acid prediction on less-studied proteins - where could these gains come from?
Great finding led by @TuXinming@phylo_bio
BREAKING: Nvidia's, $NVDA, Board of Directors announces it does not intend to reinstate Jensen Huang as CEO of the company.
The board also says they will not be accepting any questions regarding Jensen Huang on their earnings call.
We are so excited to share the formation of MLBio! 🚀🚀
Looking forward to seeing what comes of merging two very vibrant scientific communities 🧬🔬
What a fantastic effort to do this alongside @ebetica@pkoo562 and @david_a_knowles
Sign up or follow @workshopmlbio to stay up to date!
📣 MLCB + MLSB are joining forces under MLBio.org ! 🧬🤖
The first workshop will be held 2027, Join the MLBio mailing list to stay updated on calls for papers, deadlines and more info on the first event!
groups.google.com/g/mlbio
Excited to share Germinal Multi, a framework for multi-target antibody design and rescue. We applied it to cancer resistance mutations, historical SARS-CoV-2 evolution, and paired with a viral evolutionary model, antiGen, to design against a forecasted escape variant! (1/8)
LLMs are powerful, so why do we still make them call tools to handle 3D molecules?
Introducing Nahual: a decoder-only model for any sequence of text and 3D molecules. #NeurIPS2026
Want to learn more about life sciences @OpenAI? Join me and the team on Thursday, where we'll discuss how the FDE team is accelerating life sciences with our pharma and biotech partners.
forum.openai.com/public/even…
Over the past week, I’ve been overwhelmed by the love and support of friends, industry colleagues, and people I've never met. Thank you to everyone who has shown kindness to my family and me. It means the world to me.
I came to the United States 53 years ago, and becoming an American citizen is one of the greatest gifts and proudest moments of my life. NVIDIA has been my life’s work. Building it into the company it is today alongside my colleagues has been a privilege and an honor. Nowhere but in America could a company like NVIDIA be possible. I love our country, and I love NVIDIA.
I did not live up to the standards expected of everyone at NVIDIA, and I have made serious mistakes in my personal life. I created problems for the Board that I deeply regret. I own my mistakes completely, and I am committed to cooperating with the Board’s independent investigation.
Since my departure, I’ve seen an outpouring of calls from NVIDIA’s employees, investors, business partners, and customers for me to return as CEO. Many continue to reach out to me directly as the company navigates complex technology, market, competitive, and geopolitical dynamics. NVIDIA is a once-in-a-generation company. If the Board of Directors decides that my return is in the best interest of our shareholders, our employees, the company, and America, I would be honored to answer these calls and return as CEO.
Thank you again to everyone who has shared their good wishes. I am profoundly humbled by your support. To my family: I love you, and I will spend the rest of my life being worthy of yours.
Jensen
"Claude was trained on protein sequences at scale" by @TuXinming at Phylo 🧬
Something I think has been suspected before, so it's interesting to see more evidence
If true, I'd be interested to see if/how the open model ecosystem follows suit
Looking for a few ai / cloud / tech / router/ pharma partners to early-test OpenDDE-v2 before we drop it.
It brings co-folding and design together in a single model. We’d love to team up with a few folks for third-party validation and co-announce the launch together.
Shoot me a DM if you want early access, or RT to connect us with the right people.