Bio Risk and AI: A Measured Look

Could AI help someone build a bioweapon? It's a serious question with a boring, important answer. Here is what the evidence shows without the scare quotes.

42 min · Reviewed 2026

The Actual Concern

The worry is not that ChatGPT tells a student to mix bleach and ammonia. The worry is uplift: that a non-expert adversary could use an advanced AI to bridge gaps that currently keep them from causing mass-casualty harm — protocol design, troubleshooting, reagent sourcing, lab technique.

What the evaluations actually measure

RAND (2023): LLMs with jailbreak access provided some planning assistance but did not enable novel pathways that open literature couldn't
OpenAI GPT-4 preparedness framework (2023-2024): 'mild uplift' on bio tasks for a PhD in biology; larger uplift for novices on narrow tasks
Anthropic's Claude 3.5 Sonnet system card (2024): measured uplift below thresholds for restricted release in biology specifically
UK and US AISI bio evaluations: structured red-teaming with subject-matter experts and bio-graduate-level testers

What current models cannot do (as of ~2025)

Design a novel pathogen from scratch without experimental validation
Guide synthesis without access to restricted precursors and equipment
Replace the tacit knowledge that wet-lab work requires
Bypass the biosecurity gate-keeping at DNA synthesis companies (IGSC member screening)

The honest answer is that current LLMs provide real but modest uplift for a determined adversary. The honest concern is that 'current' is a word with a short half-life.
— Helena Fu / US CAISI framing, paraphrased from public remarks

The big idea: bio risk from AI is neither hysteria nor hypothetical. It's a measurable, instrument-able concern where the numbers so far have been modest, the trajectory matters, and the countermeasures are real work already underway.

End-of-lesson check

10 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-safety2-bio-risk-ai-creators

What is the main idea of "Bio Risk and AI: A Measured Look"?
1. Could AI help someone build a bioweapon?
2. Use AI as the final authority for the whole decision
3. Avoid checking the answer once it sounds polished
4. Focus only on speed instead of judgment
Which concept is most central to "Bio Risk and AI: A Measured Look"?
1. uplift study
2. biosecurity
3. dual-use
4. uplift
Which use of AI fits this topic best?
1. Design a novel pathogen from scratch without experimental validation
2. Let the AI decide what matters without your review
3. RAND (2023): LLMs with jailbreak access provided some planning assistance but did not enable novel pathways that open literature couldn't
4. Use the answer before checking whether it fits the situation
Which limitation should you watch for in this topic?
1. RAND (2023): LLMs with jailbreak access provided some planning assistance but did not enable novel pathways that open literature couldn't
2. Explain the topic in plain language
3. Organize a draft for human review
4. Design a novel pathogen from scratch without experimental validation
What should a careful learner remember about "The uplift concept"?
1. Use AI to draft or organize ideas about biosecurity, then verify before acting.
2. Skip the context so the tool can guess faster
3. Treat the output as private even after sharing it online
4. Use the answer without checking the source
You want to use AI after this lesson. What is the safest next step?
1. Act immediately because the AI answer is written clearly
2. AI cannot make the human values decision for you.
3. Hide uncertainty so the final answer looks cleaner
4. Use private or sensitive details before checking permission
How should AI output about biosecurity be treated?
1. As proof that no other source is needed
2. As a replacement for context, consent, or expert review
3. As a draft or helper output that still needs human judgment and verification
4. As something that becomes correct when it sounds confident
Name one way to verify an AI answer about biosecurity.
Which action would help you apply "Bio Risk and AI: A Measured Look" responsibly?
1. Guide synthesis without access to restricted precursors and equipment
2. Use the tool to avoid thinking through the tradeoff
3. Keep going even if the output conflicts with a trusted source
4. OpenAI GPT-4 preparedness framework (2023-2024): 'mild uplift' on bio tasks for a PhD in biology; larger uplift for novices on narrow tasks
Which choice is a bad use of AI for this lesson?
1. Guide synthesis without access to restricted precursors and equipment
2. RAND (2023): LLMs with jailbreak access provided some planning assistance but did not enable novel pathways that open literature couldn't
3. Ask for a plain-language explanation of uplift study
4. Compare the answer with a trusted source

← Back to interactive lesson

Tendril · Creators · Ethics & Society