HeyJaredGenes, Minds, Machines
Genes, Minds, Machines: Thoughts about Science, Communication, and AI. A newsletter covering topics in biology, data visualization, effective communication, AI, and higher education.
- Indexed issues, last 90 days
- 10
- Latest publication
- Sep 15, 2026
- Audience
- Checking…
- Earliest in this view
- Jul 6, 2026
Latest issues
It still wasn’t a lab leak (opens the original)
Read excerpt
Early in the COVID pandemic there was understandable confusion over the origin of the virus causing it. The virus, SARS-CoV-2, was similar to the earlier SARS-CoV-1, which had led to illness and death in 2002–2004, but it was also sufficiently different that it wasn’t just SARS-CoV-1 reoccurring. A zoonotic origin1 seemed likely, but SARS-CoV-2 had not previously been observed in animal hosts and therefore it wasn’t immediately clear what the source was. Some researchers started wondering whethe
Anthropic has not solved the peptide-binder design problem, but maybe bi[o]hub has (opens the original)
Read excerpt
In my recent post about Claude’s protein design efforts, I said that I was looking for a 2–3 sentence explanation of how Claude consistently did better than the collective field of human protein engineers, when it was using the same tools that everybody else is using. Well, it looks like we have our answer. The answer is ESMFold2 from bi[o]hub. ESMFold2 is a new, open source protein folding model, similar to AlphaFold3, but newer. And faster. And also, apparently,
Has Anthropic solved the peptide-binder design problem? (opens the original)
Read excerpt
You know what they say about headlines that are yes/no questions. If the author felt confident the answer was yes he would have said so.1 With that out of the way, let’s talk about the recent claim by Anthropic and see what we can find out. Are we all going to use Claude for peptide-binder design going forward?<a class="image-link image2 is-viewable-img" href="https://substackcdn.com/image/fetch/$s_!FuFK!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%
I'm sorry, you're not going to die from an AI-engineered supervirus (opens the original)
Read excerpt
Opinion writer and economist Noah Smith just dropped an article about AI-designed superviruses. Oh man. I used to think Smith was a person with informed opinions, but reading his take on a topic close to my own expertise makes me question this premise. No worries though. I’m sure I’ll read his takes on inflation tomorrow and nod along. Gell-Mann amnesia is real.<a class="image-link image2 is-viewable-img" href="https://substackcdn.com/image/fetch/$s_!FlXu!,f_auto,q_auto:good,fl_progressive:steep
Protein language models are overly constrained by covariation (opens the original)
Read excerpt
By many measures, protein language models (pLMs) perform exceptionally well at various tasks in protein research. They are great for homology search, functional classification, and even contact prediction. They can also be useful in evaluating individual mutations, though the track record here is more mixed. While pLMs appear to be excellent at separating viable from inviable mutations, they are quite bad at predicting mutations that enable or improve novel function. A new paper by Berry et al.<
Publishing over time
Last 90 days. Choose a month to open its work.
Recurring subjects
Named in the text we hold. One piece can cover several.
Audience
No verified audience measurement yet.
About this data
Counts cover the work we have indexed. Tone needs enough text and a confident classification. Excerpts and episode notes are not full articles or transcripts.
Identity or attribution wrong? Suggest a correction.