Oct 23, 2026 · 6 min · 9 segments
Claude designed three hundred thousand proteins in sixty-four hours. Seventeen worked. **Run time:** 6:30 **In today's episode:** 1. Claude designs 17 scorpion toxin binders; no antivenom yet 2…
Claude designs scorpion toxin binders.
OpenAI sends nearly 2,000 agents through a mouse brain atlas, a face photo that predicts cancer survival, two FDA clearances, one in breast cancer and one in cardiology, and Anthropix draft IPO numbers leak.
Anthropic says Claude designed protein binders against five scorpion toxins in 64 hours.
Scorpion stings kill thousands of people a year, and antivenom is costly and often in short supply, so a cheap design route would matter.
Claude generated 318,000 designs and picked 180 for testing.
The human team added 31 more.
17 bound their target, about 8%.
The two best, against a Mexican scorpion toxin called CN2, bound in the single-digit nanomolar range, near the site where a known neutralizing antibody sits.
Now the limits.
Humans wrote the first prompt and four follow-ups, and Clawed ran on its own for the first 24 hours.
Every test used lab-made toxin, not venom.
Nobody checked neutralization in cells or animals, and not one multi-toxin design worked.
Binding is the first gate, not the last.
This is a signal for protein design and noise for antivenom, because nothing here has been shown to stop a sting.
Claude designs scorpion toxin binders.
OpenAI sends nearly 2,000 agents through a mouse brain atlas, a face photo that predicts cancer survival, two FDA clearances, one in breast cancer and one in cardiology, and Anthropix draft IPO numbers leak.
Anthropic says Claude designed protein binders against five scorpion toxins in 64 hours.
Scorpion stings kill thousands of people a year, and antivenom is costly and often in short supply, so a cheap design route would matter.
Claude generated 318,000 designs and picked 180 for testing.
The human team added 31 more.
17 bound their target, about 8%.
The two best, against a Mexican scorpion toxin called CN2, bound in the single-digit nanomolar range, near the site where a known neutralizing antibody sits.
Now the limits.
Humans wrote the first prompt and four follow-ups, and Clawed ran on its own for the first 24 hours.
Every test used lab-made toxin, not venom.
Nobody checked neutralization in cells or animals, and not one multi-toxin design worked.
Binding is the first gate, not the last.
This is a signal for protein design and noise for antivenom, because nothing here has been shown to stop a sting.
The rest of this transcript — segmented and speaker-labeled, so you land on the exact moment something was said
Search every transcript — by keyword, by phrase, or by meaning, across every show Radar indexes
Trends — what is surging across podcasts, measured against its own baseline
Alerts — when a name you follow appears in a newly indexed episode
No account is needed to search Radar.