Can Large Language Models Design Biological Weapons? Evaluating Moremi Bio — mentioned by esseph

Fri, 11 Sep 2026 17:50:46 GMT

It is apparently a big deal. https://openai.com/index/building-an-early-warning-system-fo... https://www.rand.org/pubs/research_reports/RRA2977-1.html --- "Prompting Moremi Bio Agent without the safety guardrails to specifically design novel toxic substances, our study generated 1020 novel toxic proteins and 5,000 toxic small molecules. In-depth computational toxicity assessments revealed that all the proteins scored high in toxicity, with several closely matching known toxins such as ricin, diphtheria toxin, and disintegrin-based snake venom proteins." "The findings from this toxicity…

Paper and discussion history. A mention is not an endorsement.

Can Large Language Models Design Biological Weapons? Evaluating Moremi Bio — mentioned by esseph

Sat, 28 Feb 2026 20:58:16 GMT

Oh yeah? https://theconversation.com/an-illegal-bioweapons-lab-was-fo... https://abc30.com/post/illegal-reedley-biolab-connected-lab-... Here's a paper: https://arxiv.org/abs/2505.17154

Paper and discussion history. A mention is not an endorsement.

Can Large Language Models Design Biological Weapons? Evaluating Moremi Bio · HackerPapers discussions

Can Large Language Models Design Biological Weapons? Evaluating Moremi Bio — mentioned by esseph

Can Large Language Models Design Biological Weapons? Evaluating Moremi Bio — mentioned by esseph