A startup built an 8,000-square-foot lab in just 30 days to test molecules proposed by AI, it can now measure how often they work in living organisms in about 72 hours
Summary
一家初创公司在30天内建成8000平方英尺的实验室，用于测试AI提出的分子，目前可在约72小时内测量这些分子在活体生物中的有效率。
Similar Articles
@robertnishihara: I learned recently that @onepot_ai can synthesize and deliver custom molecules in 5 days, which is incredibly fast. Nor…
Onepot AI can synthesize and deliver custom molecules in just 5 days by combining robotic synthesis with large-scale ML inference on Anyscale, dramatically accelerating drug discovery.
@seclink: https://x.com/seclink/status/2057086514975404108
Anthropic engineer shared development experience of long-duration AI agents, including multi-role division and independent evaluators, enabling AI to automatically generate complete applications within 3-5 hours, with a 12x improvement in continuous operation capability.
Teams of AI agents boost speed of research
AI systems using teams of agents, like Google's Co-Scientist and FutureHouse's Robin, can accelerate drug repurposing research by developing hypotheses, proposing experiments, and analyzing data in hours instead of months.
A five-person investment team with almost no biology experience used Claude to design 318,484 proteins in just 64 hours, coordinating over 300 AI agents. Independent laboratories tested 211 candidates and confirmed 17 could bind dangerous scorpion neurotoxins.
一支几乎没有生物学背景的五人投资团队利用 Claude 协调 300 多个 AI 智能体，在 64 小时内设计了 318,484 种蛋白质，其中 17 种经独立实验室验证可结合危险的蝎子神经毒素。
In just 100 days, AI crossed into real medical work. 37,000 agents searched 55,000 trials for new treatments, an AI-designed pulmonary fibrosis drug entered Phase III, and an autonomous medical agent beat doctors on ER diagnosis, 87.8% to 78.1%
AI has achieved significant milestones in medical applications within 100 days, including agents searching clinical trials, an AI-designed drug entering Phase III, and an autonomous agent surpassing doctors in emergency diagnosis.