Tom Roseberry

bio x hardware x ai | cofounder and cto at olio labs | former neuralink & loyal | neuro phd

| discover and build beautiful things

[Tom Roseberry @TomRoseberry789]

@mike64_t to me the danger is more the slop cannon / infinite monkeys on typewriters / unintended consequences. we have something that can produce a TON of content, and statistically some of it could be really bad

[Tom Roseberry @TomRoseberry789]

Just tell it like it is @AnthropicAI - "ANY biological research with the current best model is strictly forbidden. You may use the prior best model, which has been nerfed."

[Tom Roseberry @TomRoseberry789]

@stevemagness Worlds colliding - Howard was on my thesis committee. So cool to see you cite him, thanks for the post

[Tom Roseberry @TomRoseberry789]

@Farshchi What changed?

[Tom Roseberry @TomRoseberry789]

@Ronalfa My prediction is it gets easier and easier to go vertical and the ones with a mission will win

[Tom Roseberry @TomRoseberry789]

Actually a decent number of labs are starting to do this on their own - they're just not talking about it much. At this point it's "put a camera on it and train a yolo/resnet model". These are of course more computationally-abled labs, but it's happening.

Also @transfyrai doing this

[Dave A Ricks @DaveARicks]

@CRISPR_LuCas Best summary of this finding and the concerns expressed by many about the way this has been framed and disclosed…”The hard part, and where the real discoveries come from, is figuring out what the system actually does.”

[Tom Roseberry @TomRoseberry789]

Feeling sick: skip it. Feeling tired: start with the warmup and see how it feels at 20 min - modify or stop if it's not shaking off, but most of the time things start feeling better. Some of my best workouts were when I felt like trash beforehand. Especially in running there really isn't "half-assing it" - all mileage counts.

[Tom Roseberry @TomRoseberry789]

@mardinly Pleased to confirm that Alan's DNA sequence is indeed cool

[Tom Roseberry @TomRoseberry789]

@jrkelly @Ginkgo absolutely!

[Tom Roseberry @TomRoseberry789]

So stoked about the possibilities here. Awesome team, huge opportunity

[Debesh Mandal @debesh]

The reason mRNA can't cure more diseases? Delivery.

We built NGX1 to deliver mRNA to any cell in the body using AI and multivalent physics.

[Tom Roseberry @TomRoseberry789]

@Brady_H That's just because running doesn't make you need to take a shit

[Tom Roseberry @TomRoseberry789]

OSS supercharged software development. Imagine if we did the same with biology

[nature @Nature]

An AI system trained on more than 20,000 protein structures from pharmaceutical companies outperforms AlphaFold-like models that use only public data

https://t.co/TGgCOhO3GO

[Melinda B. Chu @MelindaBChu1]

Since you believe you / AI is going to cure most major diseases in 5-10 years**, then go to hospice or cancer ward and explain the benefits of pacing AI to a human cancer patient (not a shrimp) that is dying.

Extreme hubris and God complex. Not only am I going to cure you, but on my timeline or else you die.

**Even if Anthropic focuses all its resources hundreds of billions on developing 1 drug, you won’t have 1 drug or “cure” in 5 years.

[Tom Roseberry @TomRoseberry789]

how plastic are the actual synapses of the fruit fly? the connectome is connections, and then people added artificial plasticity functions. I would bet that those plasticity functions would be maladaptive to being a fly, particularly wrt its innate motor programs. people just took this connectome and made an ANN out of it. it's still fun though

[Tom Roseberry @TomRoseberry789]

@mSanterre good thing I filed that provisional last week

[alex rubinsteyn @iskander]

New coding safety filters on Opus refuse to do biology

I guess this might actually be the end of the line for me with Claude?

[Tom Roseberry @TomRoseberry789]

@drugmonkeyblog Says in the technical paper he used CRL

[Tom Roseberry @TomRoseberry789]

You want to unlock AIxBio? This is more important than the next docking model.

[Ruxandra Teslo 🧬 @RuxandraTeslo]

In my latest @nytimes article, I wrote how Phase I trials in the US are broken and this being the biggest blocker to cancer cures. The good news: we can borrow from Australia, which keeps patients safe while moving trials faster. W/ @kroetscha for @IFP, we mapped out how.

Before getting into the weeds: why do Phase I trials matter so much?

1/ Phase I trials enable iterative loops of learning.
Each patient generates information researchers can use to refine the drug, rethink the target, adjust the dose, or redesign the next experiment. Faster Phase I trials mean faster feedback between the clinic and the lab and better drugs.

2/ Phase I is also a crucial financing milestone.
Small biotechs often have only a limited runway and getting encouraging human data can unlock the capital needed for further development. This is often the difference between survival and death for a small biotech.

3/ Reforming Phase I trials would pave the way to personalised medicine.
Sequencing, biological engineering and A.I. make increasingly personalized therapies possible. But our regulatory system was mostly built for standardized drugs tested in large populations.

Crucially, Australia is an important counterexample to the idea that faster trials must mean less safety.

We can learn from them!

1/ Depending on modality, Phase I trials can begin 6–12 months sooner there, at substantially lower cost. Australia has run more than 18,000 trials since 2006, with no evidence that this faster system has produced worse safety outcomes.

2/ Australian trial volume has increased 2x in the last decade, driven by American companies taking their studies there.

What does Australia do well?

1/ Most important, is Australia’s Clinical Trial Notification Pathway (CTN). Instead of submitting an IND package to their national drug regulator, sponsors simply notify the regulator that they are starting the study. Studies are reviewed by local ethics boards.

2/ Australia embraces a more risk-proportionate approach to study oversight. Requirements for Phase I should not be the same as those for later stage trials commercial drugs, and Australian system implements this distinction well.

3/ In Australia, Phase I studies are formally exempt from full manufacturing requirements, which can 10x costs for some drugs. In the United States, the situation is more complicated. Most sponsors end up implementing near commercial-scale manufacturing.

So what can the United States do?

1/ First: create an Australian-style notification pathway for appropriate Phase I trials.
Instead of requiring every study to pass through the full traditional FDA review pathway that American companies have to go through, qualified institutions could oversee scientific and ethical review.

2/ Formally exempt Phase I trials from commercial-scale manufacturing requirements and replace them with phase-appropriate manufacturing standards.

3/ Make FDA expectations much more explicit.
Sponsors over-engineer studies because they do not know what reviewers will accept. FDA should publish much clearer standards of what is expected.

4/ Operation TrialBlazer, launched by HHS in June, is important for achieving this, by proposing an Australian-like Expedited IND pathway.

5/ But more lasting reform will require Congress.
First, the FDA will need explicit authorization to rely on the judgments of local institutions to determine whether a trial may proceed.
Second, Congress should formally amend the statutory full manufacturing requirements currently codified in section 501(a)(2)(B) of the FD&C Act (21 U.S.C. § 351(a)(2)(B)) to exempt early-phase trials.