How Far Generative AI Has Come in Drug Discovery, and How Far You Can Trust It
I published a trend report on generative AI in biotech and drug discovery. One question runs through all of it: how far can you actually trust the output?
What I build, how far I check it, and what the checking turns up. Bioinformatics, model validation, and AI agents.
⭐ Featured
I Gave Up Reading the News and Built a Team of AI Agents Instead — econ-radar Design Notes
I kept starting and stopping with economic news — not from lack of interest, but from the sheer volume of it. So I stopped trying to do it by hand and built ...
Latest posts
I Read Someone Else’s Code Before Writing My Own
I read two open-source form builders to ground the design of a small MVP. Then I had the spec reviewed by someone other than its author, and four blocking de...
I Checked My Own Manuscript With Its Own Rule
I reconciled all 120 numbers in my manuscript against committed results. For 27 of them I couldn’t trace where the value came from.
I Re-measured a Paper’s Own Number
Can an LLM stand in for an expert judge? I tested it on public data, missed the target, and found the reason wasn’t the model.
Beyond Biomedical Research, onto the AI Agent Stage: PseudoCon 2026
Our initial target metric came back at Spearman 0.04 — essentially a failure. We put that on the slides anyway.
A news harness built in a day, then grown over 20 days of running it every day
The skeleton took a day. The interesting part came after: 20 days where the frictions and failures of running it kept reshaping the design.
When your cloud AI agent can’t reach Telegram — bridging with GitHub Actions
The CCR cloud sandbox blocks outbound HTTPS to Telegram. It took me a while to figure out why, and the fix turned out to be simpler than I expected.
When your agent keeps repeating the same news — designing for freshness and dedup
The agent doesn’t know what it wrote yesterday. Without being told, it’ll run the same drug through deep analysis again today.
I dropped manual approval after two days — going fully automatic with econ-radar
I built it so nothing would go out without my approval. Two days later I dropped that, and it runs better.
I Rebuilt My Dead Blog With an AI Pair — Here’s What Actually Broke
Months ago I gave up on this blog after the environment setup defeated me. This week I sat down with an AI coding agent and we found that almost nothing was ...