aiqbench analysis
The experiment tests whether a frontier model can generate a drug candidate, and the result was negative: Claude produced some starting points but nothing close to a viable antivenom. The write-up is weak as evidence, since the team has no biology background, the model was unreleased, and the author has a commercial interest in the outcome. Readers should treat it as an anecdote about current limits in AI-driven drug discovery, not a benchmark.
Claude did not invent scorpion antivenom

An investment research firm wanted to prove AI could revolutionize drug development. So they teamed up with Anthropic to see whether an unreleased version of Claude could make scorpion antivenom. It couldn't. It came up with some promising starting points, but nothing close to an actual drug, experts tell The Verge. Citrini Research, the firm behind the experiment, admitted that "none of us could claim to know anything about AI as it related to biology." That didn't stop it from trying to make a drug from scratch - or publishing a blog post titled "We Wanted to Use Claude to Create a New Drug. Here's What Happened." The account came comple … Read the full story at The Verge.
An investment research firm wanted to prove AI could revolutionize drug development. So they teamed up with Anthropic to see whether an unreleased version of Claude could make scorpion antivenom. It couldn’t. It came up with some promising starting points, but nothing close to an actual drug, experts tell The Verge. Citrini Research, the firm behind the experiment, admitted that “none of us could claim to know anything about AI as it related to biology.” That didn’t stop it from trying to make a drug from scratch — or publishing a blog post titled “We Wanted to Use Claude to Create a New Drug. Here’s What Happened.”…
Excerpt shown under the publisher's RSS terms · 107 words · full text and figures are on the publisher's site
Related coverage

AI designs De novo design of protein binders to combat scorpion toxins with Claude
Quantum Zeitgeist · Oct 22, 2026

[AINews] DeepSeek DeepInfer: Open Source SOTA Inference running 155T toks/day/cluster making $22m/day at ~80% margin for a 81 day payback
Latent Space · Oct 21, 2026