Claude discovers a novel enzyme system with CRISPR-like repeats

> While combing through the raw DNA sequence near the RT, the agent exclaimed: “[The DNA next to the RT] is spectacular: I can see by eye a tandem repeat array … that's a CRISPR-like … repeat array?!”

I love that with AI discoveries, we can relive the discoveries from agent transcripts like this.

I'm sort of imagining future histories involving notable AI events peppered with direct quotes like these.

Current evolved Cas9 (CRISPR) variants are highly efficient and relatively unconstrained in terms of their human genome targeting coverage. Smaller nucleases and higher targeting specificity would be useful. But therapeutic use is mostly limited by delivery.

From a genetic engineering perspective, a double strand break is a double strand break (staggered or blunt) and a DNA nick is a DNA nick. For now, this is mostly a story about how AI can be used to discover new biology (which is fantastic!).

I don't understand how an LLM is able to reason about those things

LLM use language, but it can't "think" about biochemistry

I saw that LLM have reasoning capabilities, which is different from machine learning, but I don't understand how it works.

It is odd (or maybe not) that they decided to publish a marketing whitepaper rather than a more traditional journal submission + preprint. The work does appear to be sufficient for a publication, though there's a good chance a reviewer will rip into them for some of the assertions they make, but given the topic I'm sure the paper will be accepted regardless.

The market for entry-level programmers has already declined, but at least they were somewhat in demand and made reasonable salaries. Now what happens to post-docs who already make almost nothing and often get treated like crap?

This shows why biology is so much harder a problem area for LLMs than math, finding RTs is tedious but pretty doable today, they had to scope the problem down a lot from something that would be the equivalent of Navier Stokes in biology. Glad they’re doing it though, even if it’s just marketing.

I think once the models are good enough, frontier shops will kick their customers out and use the compute for themselves.

I'm worried Ai will shortly make it really easy to make targeted viruses and such.

At this pace we can open bets if we end up with War Games, Terminator, I Robot or Resident Evil.

Did Claude find this on it's own, or did somebody using Claude find it?

I’m confused why AI companies are using agents in-house for this type of research instead of partnering externally.

I guess the improvement loop is tighter and they have more control over how discoveries can be used for marketing?

But, in my mind, it begins to feel like they are setting themselves up to be “everything” companies instead of focusing on their core product…

Why is everyone quick to point out how blogs/articles are "ai slop", but no one blinks an eye at the subtle, almost deceptive or manipulative, ways these companies choose words to nudge along the narrative that their LLM systems are conscious/sentient/persons/etc? The systems they are creating are impressive enough on its own merit. There is absolutely no need to play into the populations lack of understanding even the basics of systems by using language in such a slimy way.

    We gave Claude a prompt to search through a massive database of DNA sequences for interesting new examples of RTs. Our involvement was limited to the initial prompt and the lab work, while Claude agents combed through the database, investigated the distinct RT families, and used their own judgement to identify interesting candidates.

Alternative: We prompted Claude to find patterns of distinct RT families within a database of DNA sequences. The returned data included interesting candidates.

    After 21 hours spent searching this data by roughly 950 agents using 210 million tokens, one of the agents spotted something remarkable: a repeating pattern of DNA sequences that occurs next to the gene for an odd-looking RT.

Alternative: After running 950 instances for 21 hours, one of the instances hit on a repeating pattern of DNA sequences that occurs next to the gene for an odd-looking RT.

    After further analysis and testing in our lab, we recognized that this pattern marked a previously uncharacterized enzyme system found in bacteriophages (the viruses that infect bacteria) that we call array-associated reverse transcriptases (ART).

Alternative: We took the matched pattern data to the scientist in our lab to analyze. The scientist recognized that this data pattern marked a previously uncharacterized enzyme system found in bacteriophages (the viruses that infect bacteria) that we call array-associated reverse transcriptases (ART).

Maybe give more credit to where it is due, the actual real people scientist that verified data.

I recently heard Anthropic quietly setup its own bio lab.

That it’s plausible that they’ll move from selling tokens as their primary source of revenue to building frontier models to do cutting edge research, and using the research as their primary source of revenue rather than release the models. Because it’ll be far less of a race to the bottom than commodified tokens used by the general public.

Will be interesting to see how this all unfolds. (No pun intended, but there is a funny one there…)

Can't wait for OpenAI to publish a breakthrough in biochem...

The ball is on their court

It's clear Dario believes that the solution to AI's PR problem is to cure cancer. Or invent other revolutionary medical treatments. They're going to heavily promote every step along the way no matter how small or far away from commercialization they are, like this one.

No doubt that curing cancer would help, but I think the timeline might be a little too long. Even RSI AGI will not be able to get new medical treatments to market instantly. Real world testing takes a long time and is an unavoidable part of the process.

Very cool! However, the amazing absence of results makes me question whether they've got a Nature letter forthcoming or whether they know that another AI lab has a similar finding...

I'm getting tired of the marketing.

There are so many people involved on this yet we still say things like "Claude did", we need to start waking up and being more real about how we are still in "AI + Human" land.

What's wrong with saying "A team of researchers backed by Anthropic using Claude discovers a novel enzyme system with CRISPR-like repeats" or, ffs, mention the lead researcher in the headline?

From ravid shwartz ziv:

https://x.com/ziv_ravid/status/2102844800345251858

"Investigating the novel enzyme incident in our SF lab [2027]"

LLMs are really good at discovering patterns on huge dataset. Google also had similair breakthrough discoveries they stopped marketing them

Pacing that frontier with some bioengineering gain of function

when they say "claude" what model do they mean ?

no mention of opus/mythos/fable or anything..

Was he paid to review the paper? His praise reads very unauthentic.

> After reviewing the pre-print, Feng Zhang, one of the pioneers of CRISPR genome editing and a professor at MIT and the Broad Institute said:

> This is an exciting example of how AI agents can contribute to biological discovery. The identification of RNA-repeat arrays associated with reverse transcriptases is genuinely intriguing and merits further investigation. I hope this work encourages more scientists to explore how AI can support their research.

Don't use it for biology, Dario said, as he turned humans into Teenage Mutant Ninja Turtles.. I reckon that soon, he too will return to dimension X.

This is great, but I can't help but wonder if we're going to have another post next week with a lab complaining that they were about to publish this same finding, and they had Claude proofread their paper, and whoops how'd that get into Anthropic's training data?

I think this approach of actually doing useful science is better PR than hiring an army of influencers to shill for you, OpenAI style.

Generally speaking, hiring an army of influencers to shill for you results in bad PR, and comments like this one.

I'm sorry but this would be a mediocre paper at best. And if this were a student presenting this for a qualifying exam, you can bet a committee would be ripping them a new one for presenting this with no understanding of what it does.

> Anthropic sets up Bay Area lab beyond computer simulation work, two sources say

> Startup aims for Claude AI to direct robots in lab environments, one source says

> Company to stop short of clinical trials to avoid drugmaker competition, life sciences head says

https://www.reuters.com/world/anthropic-quietly-sets-up-biol...

Aren't there unlimited mechanisms like this? Isn't this why Doudna isn't a billionaire (you can patent something, but it's easy to create another one and patent it separately)?

I wish we could discuss this in a way that didn't immediately devolve into people shouting up or shouting down that this is either meaningless or singularity.

Caveating I'm not a biologist, but my understanding of the way this kind of thing works right now is a basic three-step process:

1) Find molecules and DNA/RNA sequences in the wild and catalog them.

2) Discover interesting subsequences among these.

3) Figure out whether any useful applications can come from what was discovered.

All three of these generally take a long time. Systematic automatic analysis of known databases speeds up and removes some of the luck from 2. But 1 and 3 are still long poles. 1 has the further issue that we usually discover these in existing organisms. I recall much of the outcry over tropical deforestation back in the 90s and replacing of rainforests with palm oil monoculture today is that the vast majority of terrestrial biodiversity is found in rainforests, and destroying them at industrial scale risks losing potentially useful molecules forever. 3 has the problem that you need to conduct physical experiments, and are limited by the speed of biochemical reactions no matter what and by the speed at which human subjects can be found and ethically experimented on assuming we care about being ethical.

A lot of good can come of this, but I don't see a path to singularity here, assuming we're talking the original Kurzweil meaning there of all technological progress that will ever happen all happening at once. Data collection and experimentation on living subjects, human or not, can only happen so fast, regardless of automation. It's not computational. Whenever you have to interface with the real world, you're now working at the speed of the real world, not the speed of electricity. CRISPR was discovered in 1987 and first used to edit a gene sequence in a human zygote in 2015. I'm sure there are plenty of ways to make the candidate discovery to human application step not take three decades, but it's never going to be three months, either.

[flagged]

[dead]

[dead]

[dead]

[dead]

[flagged]

[flagged]

This work seems directly dangerous to me?

In a year or two, articles like this will either be artifacts from peak hype or evidence of the beginning of the singularity. Right?

Fake news to pump up their share price. You can't trust any news about A.I. these days, especially near their IPOs.

This A.I. hype makes the Internet Bubble look like a walk in the park.