🔬生物安全是一场AI军备竞赛——Radical Numerics CEO Eric Nguyen
Latent Space对话Radical Numerics联合创始人Eric Nguyen，谈基因组语言模型Evo/Evo 2生成功能性病毒，以及长上下文如何解锁生物智能。
中文处理结果
OpenAI → Hugging Face 攻击事件让人们开始问“我们还需要担心什么？”，而 Anthropic 的过滤器标记了两件事：网络安全和生物学。那么自然的问题是：生物安全呢？
Clem Delangue 主张，网络战防御能力必须开放，并跟上前沿模型的攻击能力。
Radical Numerics 联合创始人 Eric Nguyen 与我们坐下来，解释了为什么那些提升生物学能力的模型，同样也能让防御不至于落后。
**从零构建病毒**
在斯坦福期间，Eric 长期无法推动基因组语言模型（GLM）取得进展。生物学家不相信它会奏效，不认为其输出可以被验证，也看不到在他们已有能力之外的重要应用。他持续推动，最终帮助领导了 Evo 的开发，并在 Arc Institute 为 Evo 2 做出贡献。这些模型后来被 Arc/斯坦福的另一支团队用于生成完整的噬菌体基因组，并合成出有功能的病毒！
**长上下文解锁生物智能**
早期的 ChatGPT 会输出诗歌和邮件，而 Evo 和 Evo-2 这样的早期 DNA 语言模型可以从零构建一个基因组。然而，DNA 与自然语言不同，它的字母表非常小（4 个字符 ACTG），而序列非常长：
- 人类平均基因为 60K
- 长的可达 2.3M
- 整个人类基因组约 3B。
长上下文模型的创新大约在 3 年前使这一切成为可能（脚注：striped hyena），远早于前沿实验室构建 1M+ 上下文模型。
改编自 Wikipedia：Genome Size
如今，Eric 和其他 AI x Bio 的杰出人士1 创立了 Radical Numerics，旨在构建并扩展 GLM，以解决广泛的生物学问题，远远超出生成 DNA 的范围。
**用 DNA 思考**
他们的 GLM 在 RNA 和蛋白质方面已经表现相当不错，因为 DNA 序列中存在基因（执行多种功能的 RNA 序列）和编码蛋白质的特定基因的清晰标记。这意味着，这些模型在尚未尝试训练其他模态（如 3D 蛋白质结构、表观遗传学和自然语言）之前，就已经泛化到多种“语言”。
如果一个模型用 DNA 语言思考，也许它也能理解环境在不同基因组上留下的印记？也许该模型已经学到了不同序列之间的功能关系，并能据此外推到新的序列？
原始正文
🔬Bio-security is an AI Arms Race - Eric Nguyen (CEO, Radical Numerics)
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.
Adapted from Wikipedia: Genome Size
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
1
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.