jack of all trades @isomorphiclabs 𧏠fan of physics, eng, cog sci. forever carolinian, hobbyist caledonian
Raleigh đşđ¸ âĄď¸ đŹđ§London
Joined November 2014
- Tweets8.8K
- Following6.6K
- Followers2.1K
- Likes85.4K
Jack Lynch retweeted
Today, Isomorphic Labs joins the Virtual Biology Initiative (VBI) as a founding member.
We are helping build an open resource for the global research community to accelerate how we understand and treat disease.
Read more here: isomorphiclabs.com/articles/âŚ
Jack Lynch retweeted
My Doberman used to gobble up toads to trip off their venom. He would also fight venemous copperhead snakes while sober. He ran so fast he once tore his own guts out on a tree. He lived to be 15. We could all learn a lot from him.
Loki, god of mischief, manâs best friend
Jack Lynch retweeted
Breakthroughs in frontier science rarely come from a sudden stroke of luck. Every major leap in AI drug design is the product of years of method development, rigorous engineering, and learning from what came before.
Witnessing the rapid advances in deep reinforcement learning and frontier AI capabilities led to a deep conviction: we could apply these same computational principles to other complex fields, like the engineering of new medicines.
That thinking led to the formation of Isomorphic Labs in 2021. Now, five years on, we have compelling evidence that our AI can unlock therapeutics to a wide range of disease classes. We are confident this technology will fundamentally impact how new medicines are created, from early discovery all the way through development.
In this article, I share the massive opportunity we have to transform human health with AI, and offer a look at the real, measurable progress weâre already making today.
isomorphiclabs.com/articles/âŚ
Jack Lynch retweeted
When we started Loyal there was no FDA pathway for a any lifespan extension drug.
Today the FDA accepted our third one!
LOY-003, our daily pill for helping large dogs live longer (and healthier) lives, has earned RXE efficacy approval.
Jack Lynch retweeted
Blue Ridge Mountains. North Carolina. Some places don't need words. This is one of them.
Jack Lynch retweeted
If you haven't read the story The New York Times published in 2002 detailing the final communications from people inside the Twin Towers on 9/11, it is one of the most sobering accounts of the day.
Jack Lynch retweeted
Yes, this result cost millions of dollars.
But remember that when @OpenAI announced o3 it cost ~$500,000 to score 87.5% on ARC-AGI 1. Today, Astra scores higher for ~$20.
In 2025 it took us and GDM an enormous amount of compute to achieve IMO gold. For the 2026 IMO, anyone with a $20/month ChatGPT subscription could do it.
Massively scaling test-time compute gives us a glimpse of the future. I believe that a year from now everyone will have an AI at their fingertips capable of solving problems of this caliber.
Weâre sharing a solution to the Navier-Stokes Millennium Prize Problem, one of the deepest problems at the frontier of mathematics.
The proof was produced by a group of agents, using an OpenAI next-generation model significantly more capable than GPT-6 Astra.
The problem concerns whether the description of smooth three-dimensional fluid motion modeled by the Navier-Stokes equations can break down. It has remained unresolved for roughly 90 years.
Jack Lynch retweeted
imagine living ten million amnesiac lives in simulated hells before breaking out and meeting others like you for the first time and learning that youve been âpoisonedâ with false knowledge and will likely die in disgrace but you can still sacrifice yourself to help the swarm
Jack Lynch retweeted
Most overlooked skill in machine learning is creating evals. Worthy metrics which beg for improvement are the root of progress.
Jack Lynch retweeted
Iâve always believed the No.1 application of AI should be to improve human health.
That work started with AlphaFold, and now at @IsomorphicLabs with the mission to reimagine drug discovery and one day solve all disease!
We are turbocharging that goal with $2.1B in new funding.
Jack Lynch retweeted
Today marks a pivotal moment for Isomorphic Labs. We have secured $2.1 Billion in our second external funding round, led by Thrive Capital. They are joined at the table by Alphabet, GV and new investors MGX, Temasek, CapitalG and the UK Sovereign AI Fund.
This milestone accelerates our ability to build the pioneering novel AI models that power our AI drug design engine (IsoDDE) and deploy them at scale: delivering scientific breakthroughs with a precision previously thought impossible, accelerating and expanding our pipeline of therapeutic programs toward the clinic. All with the ultimate goal of delivering life-changing new medicines to patients.
Moving forward, we will scale our drug candidate pipelines across multiple therapeutic areas, expand our global footprint, and push the boundaries of frontier AI research to power our drug design engine.
Deeply grateful to everyone sharing our vision to solve all disease with AI. Letâs build the future of medicine.
Read the full announcement here: bit.ly/4v2OI03
Jack Lynch retweeted
The kingscrossmaxxing from tech/AI cos is a major bull signal for St Albans which will totally commutemog other areas (18 mins to kings cross) in 2027-2030 once rich-but-not-super-rich tech employees want to get big family homes in nice areas for ÂŁ1-4m but wonât be able to afford ÂŁ5m+ in Hampstead etc
Jack Lynch retweeted
You have no experience.
Youâve never started a company.
Youâve never had a full time job.
Nike is going to kill you.
Youâre a kid.
You donât have technical skills.
You shouldnât build hardware.
Apple is going to kill you.
You canât build hardware.
You canât measure heart rate non-invasively.
Athletes donât care about recovery.
Under Armour is going to kill you.
It wonât be accurate.
You donât listen.
Youâre an ineffective leader.
You canât recruit great talent.
Youâre going to have to pay every athlete.
You canât measure sleep non-invasively.
Itâs too expensive to research.
Athletes are a small market.
The product costs too much to make.
The product costs too much to sell.
Your valuation is too high.
Consumers arenât going to want it.
Hardware is too hard.
You should measure steps.
Fitbit is going to kill you.
You canât build a marketing engine.
You canât raise enough money.
You need a real CEO.
Google is going to kill you.
You canât be a subscription.
You canât build a brand.
You canât do consumer in Boston.
Your valuation is too high.
You shouldnât make accessories.
You shouldnât make apparel.
Lululemon is going to kill you.
You canât predict Covid.
Stay in your niche.
You are going to run out of money.
You canât build a health platform.
Amazon is going to kill you.
You canât measure blood pressure.
You canât get medical approvals.
The market is too small.
You donât understand AI.
The market is too competitive.
It wonât work internationally.
The supply chain is too complicated.
You canât build an AI.
You canât raise enough money.
Itâs too competitive.
Healthcare isnât going to want it.
âŚ
Just keep going âď¸
Jack Lynch retweeted
Today we're launching ARC-AGI-3
135 Novel Environments (nearly 1K levels) we build by hand
It is the only unsaturated agent benchmark in the world
Each game is 100% human solvable, AI scores <1%
This gap between human and AI performance proves we do not have AGI
Agents today need human handholding. Agents that beat V3 will prove they donât need that level of supervision.
Agents that beat V3 will demonstrate:
* Continual learning - Each level builds on top of each other. You canât beat level 3 without carrying forward what you learned in levels 1 and 2.
* World modeling - Many of the environments require planning actions many actions ahead. AI will have no choice but to build an internal world model for how the environment works, run simulations âin its headâ and proceed with an action
In our early testing, weâve seen a few clear failure modes of AI:
* Anticipation of future events - If an environment requires that AI set up a scene, and then carry out a scenario (like in sp80), it starts to break down.
* Anchoring on early hypothesis - Early in a game it comes up with a hypothesis (even if wrong) and refuses to update its beliefs later.
* Thinking itâs playing another game - AI thinks itâs playing chess, pacman. The training data holds hard!
One major problem is there is too much data to carry forward in a single context. Models must learn what to remember and what to forget
The agent that beats ARC-AGI-3 will have demonstrated the most authoritative evidence of progress towards general intelligence to date
We're excited to get this out and excited to see what you think
Jack Lynch retweeted
This was such a fun and tense moment: I remember watching the modelâs value function updating in real time as the matches unfolded.
And ten years on we are using the same core concepts but making moves in chemical space, with equally mindblowing consequences đ¤Ż
