Solving molecular discovery

Joined February 2025
Bindwell retweeted
We built an 8000 sqft. high-throughput wet-lab in 30 days, to solve molecular discovery - starting with pesticides. Most teams in drug-discovery don’t receive target-organism verification until clinical trials. Pesticides allow us to rapidly validate our model in the target organism directly. With the help of our high-throughput lab, we were able to generate compounds that killed a $13 billion pest, the Fall Armyworm. We believe that the bitter lesson is coming for biology.
186
176
123
1,416
659,323
Bindwell retweeted
Biology today feels like the 2012 crispr-days on steroids. But even in that context Navvye and Tyler’s Bindwell is knocking it out of the park!!
1) Today we're announcing Atomwell, our state-of-the-art foundation model for predicting experimental outcomes, alongside scaling laws for molecular discovery. We trained models from 800M to 9B parameters on ~80M experimental measurements, and found clean scaling laws in both model size and data.
2
2
7
517
Believe in the bitter lesson
1) Today we're announcing Atomwell, our state-of-the-art foundation model for predicting experimental outcomes, alongside scaling laws for molecular discovery. We trained models from 800M to 9B parameters on ~80M experimental measurements, and found clean scaling laws in both model size and data.
1
6
459
Bindwell retweeted
I met an 18yo startup founder from India who dropped out of Caltech to build foundation models that synthesize better, safer pesticides. Paul Graham himself tweeted about it. Agency is the only moat. 99% of kids will never read a book and 1% are super-geniuses.
57
136
23
2,413
312,992