RJ Honicky
Frontier Insights
Frontier Thesis: AI is converting wet-lab discovery into a software paradigm. The defensible investment is not end-to-end drug creation, but an autonomous discovery OS—closing the hypothesis-simulation-experiment loop across chemistry, biology, and materials.
Strategic Posture: Operate as a neutral infrastructure layer (e.g., Chai Discovery). Win by compounding active learning with world models to systematically compress trial-and-error cycles in high-value, intractable design spaces.
Critical Risks: Downstream reality is the choke point. Value stalls on wet-lab logistics, sparse ground-truth data, validator vulnerabilities, and real-world manufacturability—silicon speed remains tethered to physical verification latency.
Key Views & Dialogues
🔬Bio-security is an AI Arms Race - Eric Nguyen (CEO, Radical Numerics)
Radical Numerics is positioning genome language models to move from reading DNA to designing functional sequences, with Omni’s post-training targeting variant effects in long-range, non-coding regions. The potential wedge is practical prediction across the roughly 98% of the human genome outside coding regions, while wet-lab validation, benchmark leakage, false positives, and biosecurity remain material execution risks.
View summary (7)
Radical Numerics is betting that genome language models will progress from reading DNA to designing it, with defense built into the same technical approach. Eric Nguyen traces the path from HyenaDNA’s million-token context to Evo’s generative genomics and Omni’s task alignment. Because a model that designs biological function may also recognize it, the company has adopted a “dual mandate” spanning scientific discovery, human health, and biosecurity.
Omni’s claimed breakthrough is not merely scale but the post-training that turns a foundation model into a usable genomic system. Evo and Evo 2 showed broad capabilities yet could lose to specialized models; Omni uses task-specific formatting, special tokens, supervised examples, and question-and-answer structures to answer practical questions such as whether a mutation causes disease. Nguyen says this has pushed it toward state-of-the-art performance across variant-effect tasks, especially in long-range, non-coding DNA.
The high-value wedge is the roughly 98% of the human genome outside protein-coding regions, where conventional interpretation remains weakest. Coding regions constitute only about 1.5–2% of the genome, while many disease-associated variants sit in regulatory regions whose effects depend on context. Omni compares the likelihood of wild-type and mutated sequences, converts the difference into a “surprise factor,” and adds aligned training to produce directly usable predictions.
Radical’s most speculative design result treats biological optimization trajectories as a genomic version of chain-of-thought reasoning. Given RNA aptamers ranked from low to progressively higher fitness, the model continued the trajectory and generated plausible sequences with scores beyond those shown during training. Nguyen repeatedly hedges the result—the candidates still require wet-lab validation—but argues that the paradigm could extend to antimicrobial phages and selective rare-earth-binding proteins.
Long biological context, rather than isolated protein structure, is the company’s proposed technical advantage. Nguyen describes DNA as an “imprint of the physical world”: upstream regulatory regions, neighboring genes, organism identity, and evolutionary history can constrain which designs are plausible. That framing supports a unified model spanning DNA, RNA, proteins, epigenomics, metabolomics, and eventually natural language, rather than a collection of single-modality tools.
Biosecurity is both a mission commitment and a potential product category, but the speakers do not pretend the screening problem is solved. Radical divides defense into detection, attribution, countermeasures, and government-level deterrence; its models are intended to recognize functional danger even when a sequence no longer matches a known pathogen database. RJ’s pushback is material: at the scale of billions of sequences, false positives could obstruct legitimate research, and unlike software vulnerabilities, “we have fixed genomes” that cannot simply be patched.
Nguyen nevertheless sees an “arms race” because design capabilities are advancing while biological defense remains significantly behind. The nearer-term danger may be accidental release, although state bioweapons programs remain a wartime concern. His explicitly named bottlenecks are GPUs and a cultural one: scientists need domain expertise while retaining enough imagination to challenge entrenched workflows.