Tristan Farmer

AI for programmable biologics & protein design | Building biological intelligence | Longevity & personalised therapies | GitHub: 001TMF | UoE

[Tristan Farmer @001TMF]

Betting beyond generative models in bio.

A weekend is all it took for our biological intelligence platform to go from data —> viable antibodies. Fully closed loop design and fully autonomous. I didn’t touch a thing.

[Bryan Johnson @bryan_johnson]

If Hantavirus mutated into a global threat, it would unleash AI + biotech unlike anything we've ever seen.

> genome sequenced and public in 4 hours
> AlphaFold maps every protein target
> AI screens 10,000 drugs in 24 hrs
> 50 vaccine candidates designed simultaneously
> AI designed antibodies in days
> risk of death computed instantly
> decentralized trials launch globally
> enroll from home
> 20 countries manufacturing at once
> first doses in three weeks
> real-time dose characterization
> your genome + biomarkers determine your protocol
> variant map updates every hour

No one would wait for governments.

[Tristan Farmer @001TMF]

The reaction is somewhat warranted. Wanted my plant to grow better.

- Gave Claude a photo of it
- Found its genome
- Designed a protein to weaken DELLA repression

Guess we'll find out if it will do anything.

https://t.co/JliSfOPYVS

[Tristan Farmer @001TMF]

At this point, this biosecurity letter feels like pure theater a repeat of Mythos and Glasswing.

create the issue, then pass the liability

If it’s a real problem, more paperwork isn’t the solution.

[Tristan Farmer @001TMF]

@inferredbylisa Isn't that the primary definition of science?

[Tristan Farmer @001TMF]

@jacobkimmel Pushing biologics discovery towards compute changes a lot for the future.

[Tristan Farmer @001TMF]

What would the perplexity of bio look like, and who is it?

[Tristan Farmer @001TMF]

@p_maverick_b Feels very performative from AI labs. Same theatre as with mythos and cybersecurity. Genie is out, and now they want to defer liability? They should have pledged to be part of the screening effort.

[Tristan Farmer @001TMF]

The race is back on.
https://t.co/EVTFmb79Ll

[Jack Dent @jackdent]

I’m delighted to announce @chaidiscovery's collaboration with @pfizer. Their scientists will deploy our AI platform to accelerate drug discovery, including early access to our latest frontier model Chai-3.

You can learn more about this partnership and our momentum in @amyfeldman's feature in @Forbes out today

https://t.co/VBoynDgPCz

[Tristan Farmer @001TMF]

Biological reasoning on top of chai-3 would go crazy. Identification --> drug

[Jack Dent @jackdent]

I’m delighted to announce @chaidiscovery's collaboration with @pfizer. Their scientists will deploy our AI platform to accelerate drug discovery, including early access to our latest frontier model Chai-3.

You can learn more about this partnership and our momentum in @amyfeldman's feature in @Forbes out today

https://t.co/VBoynDgPCz

[Tristan Farmer @001TMF]

@jackdent @chaidiscovery @pfizer Blinked, and chai-3 is out. Congrats!

[Tristan Farmer @001TMF]

Welp, that was fast. Didn't Chai-2 just come out?

[Joshua Meier @joshim5]

Today we are announcing our collaboration with Pfizer to put Chai's frontier AI—including our latest model, Chai-3—directly into the hands of one of the world's leading pharmaceutical teams.

[Tristan Farmer @001TMF]

performative conscience

[Andrew Curran @AndrewCurran_]

Sam Altman, Dario Amodei, Demis Hassabis and many others have signed a letter urging Congress to increase security on orders of synthetic nucleic acids - and the equipment needed to make them - as models continue to become increasingly bio-capable.

[Tristan Farmer @001TMF]

@bayeslord For what? Genie is out, and now they want to defer liability?

[Tristan Farmer @001TMF]

Regardless, the genie is already out of the bottle. We’re in the era of advanced biologically-centric AIs, and any open-source LLM can ingest the data.

[Tristan Farmer @001TMF]

At this point, this biosecurity letter feels like pure theater a repeat of Mythos and Glasswing.

create the issue, then pass the liability

If it’s a real problem, more paperwork isn’t the solution.

[MTS @MTSlive]

SITUATION DETECTED: Sam Altman, Dario Amodei, and Demis Hassabis have signed a joint open letter calling on Congress to mandate screening of synthetic nucleic acid orders, citing AI’s rapidly improving ability to assist with biological research as an urgent biosecurity risk.

[Tristan Farmer @001TMF]

If this is the case, isn't it just GPT 5.5 without the AUP filters? Basically, KYC-based access to a less-filtered model?

[OpenAI @OpenAI]

We’re bringing new capabilities to GPT-Rosalind, a model series purpose-built for life sciences research at enterprise scale.

It brings GPT-5.5’s agentic coding and tool use together with stronger intelligence for drug discovery, analysis, design, and experimental workflows.

https://t.co/SrAJ3Mt7ka

[Tristan Farmer @001TMF]

Whats stoping us reaching direct to consumer theraputics.

Upload your genome, tumour data, and immune profile, and get a therapy built for you.

[Tristan Farmer @001TMF]

@ChrisHayduk @OmicsOmicsBlog Exciting! But how do I get my hands on Rosalind?

[Tristan Farmer @001TMF]

@CotetTudor So true. Biggest takeaway

[Tristan Farmer @001TMF]

Apple keyboard has become really painful to use. Can’t pinpoint when this started but is terrible now.

[Tristan Farmer @001TMF]

The protein AI race is playing out very differently to the LLM race.

A year ago, Chai and Latent were the frontier of antibody and binder design, and the frontier was closed. Within months, Protenix, ESM, and Boltz open-sourced the tools.

Who will win?

[Tristan Farmer @001TMF]

Alphafold once represented open science then closed AlphaFold 3 for profit. Code and weights are non-commercial only, and the lone commercial path runs through Isomorphic.

[Tristan Farmer @001TMF]

How has esm significantly outpaced alphafold database?

@demishassabis what happened to just fold them all?

[biohub @biohub]

Proteins are the machinery of life. Scientists have cataloged billions of protein sequences—but their biology is still mostly unknown.

ESM Atlas is a new way in.

6.8 billion proteins. 1.1 billion predicted structures—the largest application of AI to protein biology to date. ESM Atlas makes the uncharacterized parts of protein space searchable for the first time. And it's fully open.

Start exploring: https://t.co/n6OWfcWdHe