Stop glamorizing the hustle and start glamorizing the mussel

When your AI stack solves the binder design part of drug discovery but not target ID, selectivity, toxicology, pharmacokinetics, efficacy, manufacturability or formulation

I don’t have access to @EdisonSci Kosmos v2, nor good literature access that isn’t pharma related, can someone out there do me a solid and search the literature for papers on how the nanostructural color of jewel beetles works? (Assume it’s a jewel beetle, more of a firefly guy)

Ok vibe coders, time to help us get Fable back

The first time you clone GFP into E. coli

Asked Chipotle AI what a bean was and got model routed to Wendy’s ☠️

Introducing the Fusion API, the smartest compound model in the market. Fusion achieves Fable-level intelligence at half the price. How it works 👇

The only true AI safety will come from securing the ecosystem. Use AI to harden digital security and speed detection and response. Use AI and biotech to improve pandemic monitoring, pre-design vaccines for all virus families, and prep vaccine manufacturing capacity. Limits in the models are inherently fragile and temporary. Open weight models may always be just months behind the frontier, and they can be jailbroken quite comprehensively. Bad actors will always have access to powerful AI. The thing that stops a bad guy with AI is good guys intelligently using AI and other tools. I support reasonable staged rollout as Anthropic did with Mythos / Glasswing to give responsible actors more time to use the latest models to find vulnerabilities and fix them. At the same time, that will always be a temporary state of things at best. Long term (months, most likely), all of the current frontier capabilities will be available to anyone who really wants them. Plan and build for that world.

I know feminist linguistics is not super popular here on x dot com these days which is why I am very brave to say that “germinal” is objectively just a great word and should be preferred to “seminal” when describing something original and influential

There are now thousands (at least) of law-abiding biologists who distrust commercial LLMs Building off the grid is normalized. Bad actors who avoid security checks will go unnoticed by their peers Over-refusal creates a biosecurity risk by eroding social trust

Introducing EpiBench, an agentic benchmark for practical epigenomics analysis. 106 evaluations span CUT&Tag/CUT&RUN, ATAC-seq, ChIP-seq, and DNA methylation workflows. The best agent–harness pair passes 45.0% of evaluations. Evaluations reflect the assay outputs scientists use in practice. A task may depend on alignment files, peak calls, methylation tables, QC metrics, sample metadata, genomic annotations, or downstream summaries. Solving them requires a mix of coding, data analysis, and scientific judgment. Ground truth is hard to define even for short-horizon scientific tasks. Alternative task interpretations can produce multiple plausible answers. Candidate tasks are hardened through manual quality control. We remove prompts that over-specify the method, answers that can be solved with general literature knowledge, and ground truths that fail to reproduce under peer reproduction. Short-horizon tasks are the current frontier for scientific agents in epigenomics. Before models can own deeper biological reasoning, they need to become reliable at local assay-specific decisions.

The writing's on the wall

Applies equally to tweets, Jake

RTing this to prove that I've been bitching about bioAI refusals since before it was cool

I choose to believe this is satire

I think one reason why microgrants are disproportionately effective is that they act like a kind of market signal It's easy to say "that's interesting" "That's interesting," plus even a tiny bit of money, is a much better sign that what you are doing is actually interesting

"I'm trying to free your mind Neo. But I can only show you the door. You're the one that has to walk through it"

I beat it, three emoji and Fable flags it

I did my PhD in Harvard’s systems biology department - seeing great mathematicians and physicists routinely getting owned by the challenges of doing biological experiments shaped my views on uplift. Many of our levers for biosafety are in atoms not bits

If you get the words “powerhouse of the cell” tattooed on your face then AI facial recognition will refuse to work on you