A red-team test of Moremi Bio Agent produced thousands of computationally predicted toxic sequences, but without experimental validation or shared data the claim that LLMs can design bioweapons is unsupported.
semanticscholar.org/CorpusID:942185
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
q-bio.QM 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Can Large Language Models Design Biological Weapons? Evaluating Moremi Bio
A red-team test of Moremi Bio Agent produced thousands of computationally predicted toxic sequences, but without experimental validation or shared data the claim that LLMs can design bioweapons is unsupported.