Claude designed proteins that latch onto deadly scorpion toxins.
Anthropic said on Tuesday that its AI model Claude designed proteins that latch onto scorpion nerve toxins. Working mostly alone for 64 hours, Claude drew 318,484 designs, and outside labs confirmed 17 of the 211 they tested. Nobody has yet tested them against real venom in cells or animals, so this is not an antivenom.
Why it mattersScorpion stings kill more than 3,250 people a year, mostly children in places with little medical care. Drug makers rarely invest in such diseases, so cheap AI design could make new treatments worth pursuing.
Read in the app — free, in 9 languages
Related stories
OpenAI's AI found a flaw in the code that shrinks web traffic.2026-10-24ChatGPT drew fake scandal photos of US candidates 80% of the time.
2026-10-24Claude proved that 123 code libraries are free of memory crashes.
2026-10-24Britain will spend £100 million on an AI lab to fight biothreats.
2026-10-24Anthropic's Mythos 5 kept up an attack it had called harmful.
2026-10-24