> ## Content Index
> Fetch the complete content index at: https://adjacent.media/llms.txt
> Use this file to discover other available public pages before exploring further.

# AI-Trained Biology Models Pose Dual-Use Biosecurity Risk
- URL: https://adjacent.media/signals/ai-trained-biology-models-pose-dual-use-biosecurity-risk/
- Published: 2026-09-14T16:11:15.000Z
- Updated: 2026-09-14T16:11:15.000Z
- Description: Experts distinguish current LLMs—which lack embodied knowledge to guide weaponized pathogen design—from next-generation foundation models trained on biological datasets, which could materially lower barriers for non-state actors.
- Author: Jonathan Greene
- Tags: #signal, theme-culture, regulation, policy, ai safety

Source: [NYT > Business](https://www.nytimes.com/2026/09/14/science/ai-bioweapons.html?ref=adjacent.media) (paywall)

Experts distinguish current LLMs—which lack embodied knowledge to guide weaponized pathogen design—from next-generation foundation models trained on biological datasets, which could materially lower barriers for non-state actors. This is forcing real decisions about model architecture and access controls now, before the capability gap closes. Biosecurity researchers are already mapping which training methodologies and safety mechanisms matter most, making this a near-term governance problem, not a distant concern.