@rohanpaul_ai: New Anthropic research shows AI agents may look brilliant at code, but in biology they can fail before the science star…
Summary
Anthropic research reveals that AI agents struggle with biology databases, producing highly variable answers for the same query (e.g., Ebola sequence counts ranging from 5 to 106 vs. expected 266), but adding a repeatable retrieval tool significantly improves consistency and accuracy.
View Cached Full Text
Cached at: 06/08/26, 11:29 PM
New Anthropic research shows AI agents may look brilliant at code, but in biology they can fail before the science starts.
Strong AI agents could give very different answers to the exact same biology data request, even when nothing changed in the prompt.
In one Ebola sequence task, Claude Sonnet 4 returned 106 sequences in 1 run, then 15, then 5, while the expected answer was 266.
Those missing sequences did not just make the dataset messy, they changed the scientific story built on top of it.
One bad retrieval made the outbreak look like it traced back to 1922, instead of the manually curated result pointing to early 2014.
The biology databases were too hard to use reliably through current AI tools.
The agents often understood what they were being asked, but their answers varied a lot because they had to fight through scattered databases, hidden website rules, and fragile scripts.
The key finding is that adding a repeatable retrieval tool made agents far more accurate and much more consistent.
Anthropic (@AnthropicAI): New Science Blog: Why has AI advanced faster in coding than in biology?
To agents, bio databases are like cities built before cars—maddening to drive in because they’re designed for different traffic.
How do we build infrastructure agents can use?
Similar Articles
@AnthropicAI: New Science Blog: Why has AI advanced faster in coding than in biology? To agents, bio databases are like cities built …
Anthropic's science blog argues that AI progress in biology lags behind coding because biological data infrastructure is not designed for agents. A case study shows that adding a deterministic retrieval layer (gget virus) boosts accuracy to nearly 100%.
@rohanpaul_ai: Anthropic's new research found found that identical or similar agents can converge on the same bad decision, turning in…
Anthropic's new research finds that identical or similar AI agents can converge on the same bad decision, turning individual errors into system-wide failures, and that stronger agents don't automatically coordinate better, suggesting a need for institutional layers for agent coordination.
Jun 8, 2026SciencePaving the way for agents in biology
Anthropic researcher Laura Luebbert argues that biological data infrastructure needs to be redesigned for AI agents, using a case study where even strong models failed to reliably retrieve sequence data from NCBI Virus until a deterministic retrieval layer was added.
@rohanpaul_ai: Most AI agents are still judged by the answer they return. Apodex 1.1 from @Apodex_AI is training for something harder:…
Apodex 1.1 is an AI system that shifts focus from simple answers to completing and verifying entire jobs, with capabilities for environment scaling and agentic coordination.
@OkhayIea: Everyone's racing to build "AI scientists." So we asked a blunt question: Can today's best coding agents beat the publi…
Introduces NatureBench, a cross-disciplinary benchmark of 90 tasks from Nature papers to test AI coding agents, finding the best agent (Claude Opus 4.7) surpasses SOTA on only 17.8% of tasks and often succeeds by reducing science to supervised ML rather than genuine discovery.