Introducing Latent-X — our all-atom frontier AI model for protein binder design. State-of-the-art lab performance, widely accessible via the Latent Labs Platform. Free tier: https://t.co/NamdznPWjL Blog: https://t.co/2UkYDEe8a9 Technical report: https://t.co/0m2s3y7vwN

Some excellent points here, which I always felt applied to why AlphaFold generalizes so well. AF2 is so accurate on unseen proteins because it's trained to decode the MSA - which acts like a lossy 'memory' of the structure. Its architecture pre-bakes geometric principles that

Honoured to join Prime Minister @Keir_Starmer and Secretary of State for Business and Trade @peterkyle on the UK's business visit to India this week. My first trip to India, and what a visit! Proud to join the delegation, traveling alongside Britain’s leading companies to

Last night @nvidia CEO Jensen Huang announced $2B of investments in UK AI start-ups, including in @Latent_Labs. Not the only ace up his sleeve, Jensen also had Prime Minister @Keir_Starmer join on stage for the occasion. Pinched myself this morning, but it did happen, caught

Honored to have been nominated 35th in the @observer's A.I. Power Index 2025 of 100! Truly humbling to be part of this star-studded list. @demishassabis, @DarioAmodei, @JeffDean, @matistanis - all folks that I have admired (and now had the privilege to work with) in ML and

Our very own @SeBayesian and @SimMat20 will present at In Silico, London, on 1 October. We'll be speaking about Latent-X, our Atom-level Frontier Model for De Novo Protein Binder Design. Also featuring @amyxlu and @DominiqueLaLo, we're looking forward to it! Register for In

We're working with @nvidia to accelerate computational drug discovery. See how they are working with us and the broader UK AI ecosystem in the press release below, issued as part of the UK state visit. 🇺🇸🇬🇧

Really cool to see @nanome_inc review Latent-X in their VR environment! 💻🧬 They pick an unseen target, and find the @Latent_Labs platform generates diverse binders with highly specific biochemical interactions! 💯 Watch their discussion of the designs here:

We work with AWS to enable our partners with our frontier AI models. Right where they need them, whether that’s in our platform or deployed in their virtual private containers. Our platform let’s our users generate protein binders at the push of a button. In a free tier, open to

It's been great to talk to @TomMackenzieTV of @Bloomberg News about the launch of our protein design model and platform this morning!

In this week's #RadicalReads, @saakohl, Founder and CEO of @Latent_Labs, explores how the recently launched Latent-X model is making biology programmable by enabling scientists to design novel proteins with atomic precision directly in their browser:

Thank you @decodingbio for covering our launch and reviewing our platform on binder design tasks! The authors concluded: 'Latent Lab’s new platform speaks for itself.' Read the full review article here:

Showcasing Latent-X's breakthrough macrocycle designs. Our AI achieved an unprecedented 91-100% hit rate with single-digit micromolar binding affinities—functional binders on every single target tested. Explore our binders without logging in: https://t.co/y3rt7xJ9AP

It's been a fantastic first few days of public usage of the Latent Platform! The team has been providing white glove user support - for feedback or requests, you can reach us through our feedback channels: https://t.co/zmz4fnXas1 Also, check out our sharing feature below: You

🧬 Latent-X is our first frontier model for protein design. For mini-binders, our AI model achieved picomolar binding affinities — the strongest reported vs prior methods in head-to-head lab validation. Explore our best binders here (no login required): https://t.co/foSS9ICdyX

‘Latent Labs launches web-based AI model to democratize protein design.’ Thank you @TechCrunch and @MTemkin for the coverage. Read the full story:

It is amazing that bench scientists are being given superpowers through computational tools like Latent-X! Huge congrats to the team!!

@saakohl Congratulations - that’s amazing!

Radical portfolio company @Latent_Labs unveils Latent-X, their frontier AI model. Co-founded by AlphaFold pioneer @saakohl, Latent Labs is making biology "programmable" to accelerate drug discovery. Learn more about Latent-X here:

I love the trend of companies publishing technical reports / blogs instead of spending a year+ in peer review publishing detention - get your research OUT THERE!!!! v excited to read

🚀 Big milestone — impressive science and great to see it made so accessible. Congrats to the @Latent_Labs team!