生物安全是一场AI军备竞赛
论证要点
- Anthropic的过滤器把网络安全和生物学列为两大风险，由此引出生物安全问题：OpenAI→Hugging Face攻击后，人们开始问还该担心什么。
- Eric Nguyen在斯坦福长期推动基因组语言模型（GLM）受阻，生物学家不信其可行性、无法验证输出、也看不到超越现有手段的应用，他坚持推进并参与Evo与Evo 2。
- Arc/斯坦福团队用这些模型生成完整噬菌体基因组，并合成出有功能的病毒，证明从零构建基因组可行。
- DNA与自然语言不同：字母表只有4个字符（ACTG），序列极长——人类基因平均60K、最长2.3M、全基因组约3B；约三年前长上下文模型的创新（striped hyena）让这成为可能，早于前沿实验室做1M+上下文。
- GLM已能较好处理RNA和蛋白质，因为DNA序列中有基因和编码蛋白基因的明确标记，模型在未训练其他模态前就已泛化到多种“语言”。
- 适配体实验：只给模型看低分aptamer并逐步展示更高分，模型能自行延续轨迹并复现未展示过的高分——即“用DNA思考”的思维链。
对实践的启示
做AI应用的人应把生物安全当作与网络安全并列的前沿风险；长上下文、思维链、多模态这些在LLM上奏效的能力，正在GLM上复现并放大生物风险，防御方目前落后，需要更快的模型迭代来跟上。
作者承认的反方与局限
文章提到生物学家曾不相信GLM可行、无法验证输出、看不到超越现有能力的应用；作者也承认防御目前在这场竞赛中处于下风。
原文摘引
Clem Delangue argues that cyber-warfare defensive capabilities need to be open and to keep pace with frontier models’ attack capabilities
According to Eric, defense is currently losing this battle, but Radical Numerics argues to push the frontier harder!
So, voila: chain-of-thought, thinking in DNA!
▸ 展开原文全文（29 段，抓取自 Latent Space）
The OpenAI → Hugging Face attack has people asking “what else do we need to worry about?” and Anthropic’s filters flag two things: cyber-security and biology. The natural question is: what about bio-security, then?
Clem Delangue argues that cyber-warfare defensive capabilities need to be open and to keep pace with frontier models’ attack capabilities
Radical Numerics co-founder Eric Nguyen sat down with us and explained why the same models that increase biological capability can also keep defense from falling behind.
Building a virus from scratch
While he was at Stanford, Eric couldn’t get traction on Genomic Language Models (GLMs) for a long time. Biologists didn’t believe it would work, didn’t think they could verify the output, and didn’t see important applications beyond what they could already do. He kept pushing, eventually helping lead the development of Evo and contributing to Evo 2 at Arc Institute. Those models were later used by a separate Arc/Stanford team to generate entire bacteriophage genomes that were synthesized into functional viruses!
Long context unlocks biological intelligence
Early ChatGPT spit out poems and email, and early DNA language models like Evo and Evo-2 could build a genome from scratch. DNA is different, however, from natural language in that it has a very small alphabet (4 characters ACTG) and that its sequences are very long:
- 60K for an average human gene
- long being up to 2.3M
- the whole human genome around 3B.
Innovation in long-context models made this possible about 3 years ago (footnote: striped hyena), long before the frontier labs were building 1M+ context models.
Now Eric and other AI x Bio luminaries1 have founded Radical Numerics to build and scale GLMs to tack a wide range of biological problems, extending well beyond generating DNA.
Thinking in DNA
Their GLMs already do pretty well with RNA and protein because there are clear markers in the DNA sequence for genes (RNA sequences the perform many functions) and specific genes that encode proteins. This means that the models already generalize to multiple “languages,” before even attempting to train in other modalities, such as 3d protein structure, epigenetics and natural language.
If a model thinks in the DNA language, maybe it understands the imprint that environment left on different genomes as well? Perhaps the model has learned the functional relationship between different sequences, and could extrapolate to new sequences based on that?
And so what we wanted to showcase was that if we show the model progressively better RNAs in a series of steps with its score, right? So you have like low scores first and then you gradually move up the chain. Can the model continue that trajectory on its own? And then in the final step, does it self optimize to a point where it's like the best score it can get? That was the experiment. Can we do that? And so we took a data set, a large data set of aptamers. We held out a portion of the best performing ones and we showed it only the lower ones, but then we ranked it, right? So we showcase lower scores with the RNA aptamers and then progressively got higher, and then ask the model to just like continue with that pattern. And it turns out it was able to recapitulate some of those higher scores that we had not shown it yet.
So, voila: chain-of-thought, thinking in DNA!
The arms race
But much as long-context inference, chain-of-though and multi-modal perception unlocked sophisticated reasoning in natural language LLMs, these capabilities in GLMs are enabling increasingly sophisticated “biological intelligence,” and along with it, greater danger.
According to Eric, defense is currently losing this battle, but Radical Numerics argues to push the frontier harder!
I won’t spoil the details for you. In the episode we talk in detail about:
- Biosecurity as an arms race — and how defense can keep up
- The genome as the imprint of the environment on DNA
- Going truly multi-modal
- How chain-of-though works when you “think” in the language of DNA
Eric Nguyen: Co-founder and CEO, holding a PhD in Bioengineering & AI from Stanford University. He previously helped develop large-scale genome language models like Evo and Evo 2
Michael Poli: Chief AI Scientist, holding a Stanford PhD and a former founding scientist at Liquid AI.
Stefano Massaroli: President, a former postdoc with Yoshua Bengio and a founding team member at Liquid AI.
Armin W. Thomas: CTO, a former Stanford postdoc who worked with Chris Ré and was previously at Liquid AI.