DNA is just another language.

In Episode 32 of Built This Week, we sit down with Dov Gertz, founder of Converge Bio, to explore how generative AI is transforming drug discovery.

Every human can be represented as 3.2 billion nucleotides built from four letters: A, C, G, and T. If computers run on zeros and ones, we run on biological code.

Converge Bio is training frontier foundation models on DNA, RNA, proteins, and small molecules — helping biotech and pharma companies design better drugs, faster and cheaper.

We also demo a retro-inspired “Cell Defense Arena” game built for Converge to use at conferences.

Then we pivot into AI infrastructure and agent workflows:

The GPU bottleneck and pharma’s growing demand for compute
Why molecular AI is 5 to 10 years behind text models
How AI could reduce drug timelines from 10 years to 6 to 8
Why cancer and autoimmune diseases may benefit first
The limits of FDA regulation in shortening approval cycles
OpenClaw, multi-agent systems, and infinite AI teams
Cloud versus on prem in the era of foundation models

The big takeaway:

Chatbots are impressive.
But AI applied to biology could extend human life.

If you work in biotech, pharma, AI research, or frontier infrastructure — this episode is for you.

New episodes every Friday.

⏱ TIMESTAMPS

(0:00) DNA as code: 3.2 billion nucleotides
(0:32) Welcome to Episode 32
(1:00) Meet Dov Gertz and Converge Bio
(2:02) Demo: Cell Defense Arena game
(3:25) Converge Bio’s $33M raise and mission
(4:05) Foundation models for molecular data
(5:00) Turning DNA, RNA, and proteins into machine-readable text
(6:02) How transformers apply to biology
(7:03) 400x more DNA than text on the internet
(8:02) Who Converge’s customers are
(9:21) Faster, cheaper, better drug discovery
(10:39) The three bottlenecks: data, architecture, compute
(12:02) The future of personalized medicine
(13:02) Which diseases benefit first: cancer, diabetes, autoimmune
(14:00) Regulatory realities and clinical trial timelines
(16:30) Will AI shorten drug approval cycles?
(17:01) NVIDIA, GPUs, and scaling molecular AI
(18:30) Pharma as a new AI infrastructure consumer
(19:13) Hard pivot: OpenClaw and agentic AI
(21:26) Managing teams of AI agents
(22:20) Cloud versus on prem debate
(25:02) Why developers must adapt weekly
(29:26) Closing thoughts and where to find Converge Bio

🔗 LINKS

Converge Bio
https://converge-bio.com

Built This Week
New episodes every Friday
https://builtthisweek.com

Jordan Metzner
https://x.com/mrjmetz

Sam Nadler
https://x.com/Gravino05