Building an Early Warning System for LLM-Aided Biological Threat Creation
OpenAI published a blueprint for evaluating whether LLMs can meaningfully assist in biological threat creation. In a controlled study with biology experts and students, GPT-4 was found to provide at most mild uplift in biological threat creation accuracy. The results are inconclusive but are framed as a starting point for ongoing safety research and community deliberation on biosecurity risks from AI.
Related guides (3)
Related events (8)
Google Study Shows LLM-Generated Malware Is Getting Harder to Track and Stop
A Google security report catalogs emerging LLM-enabled cyberattack techniques including morphing malware with mutation engines, logical-flaw discovery in code, and AI-directed obfuscation networks. The report was prompted in part by a real incident where hackers used an LLM to find a zero-day in a widely used web administration tool. Separately, the UK AI Security Institute found that Claude Mythos Preview and GPT-5.5 can reliably execute attacks expected to take humans 3 hours, up from earlier 1-hour benchmarks, with performance scaling further when token limits are relaxed. The findings suggest an accelerating gap between LLM offensive capability and conventional defensive tooling.
ABC-Bench: Agentic biosecurity benchmark finds LLM agents surpass median expert humans on dual-use biology tasks
Researchers introduce ABC-Bench, a benchmark evaluating LLM agents on biosecurity-relevant biology tasks including liquid-handling robot programming, DNA fragment design, and evasion of DNA synthesis screening. All tested agents outperformed the median expert human baseline across all three tasks. Wet-lab validation confirmed that OpenAI's o4-mini-high produced scripts that successfully assembled DNA on an OpenTrons robot. The results highlight a meaningful shift in the biosecurity risk landscape as AI agents acquire practical wet-lab-adjacent capabilities.
Measuring AI's capability to accelerate biological research
OpenAI introduces a real-world evaluation framework designed to measure how AI systems can accelerate biological research in wet lab settings. The work uses GPT-5 to optimize a molecular cloning protocol as a concrete demonstration case. The framework explicitly addresses both the potential benefits and biosecurity risks of AI-assisted experimentation, positioning this as a dual-use capability assessment.
Estimating Worst-Case Frontier Risks of Open-Weight LLMs
OpenAI introduces a methodology called malicious fine-tuning (MFT) to assess worst-case risks of releasing open-weight models, specifically applied to their internal model gpt-oss. The study attempts to elicit maximum dangerous capabilities in biology and cybersecurity domains through targeted fine-tuning. This represents a systematic effort to quantify uplift risks before open-weight releases, informing OpenAI's open-weight release policy.
Preparing for future AI risks in biology
OpenAI has published a post outlining its proactive approach to assessing and mitigating biosecurity risks from advanced AI systems capable of biological applications. The piece describes capability evaluations and safeguards designed to prevent misuse of AI in biology and medicine. This reflects OpenAI's ongoing effort to get ahead of dual-use risks before capabilities reach dangerous thresholds.
OpenAI and Los Alamos National Laboratory Announce Research Partnership on Biosafety Evaluations
OpenAI and Los Alamos National Laboratory (LANL) have announced a research partnership focused on developing safety evaluations for frontier AI models. The collaboration specifically targets assessing and measuring biological capabilities and risks. LANL brings national-lab-level biosecurity expertise to the effort, which aligns with OpenAI's broader preparedness framework for catastrophic risk domains.
GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models
OpenAI published research examining the potential labor market impacts of large language models, analyzing which occupations and tasks are most exposed to automation or augmentation by GPT-class models. The study introduces a framework for assessing LLM 'exposure' across job categories, finding that a significant share of U.S. workers could see at least 50% of their tasks affected. The paper represents an early systematic attempt to quantify economic disruption potential from frontier AI systems.
A Hazard Analysis Framework for Code Synthesis Large Language Models
OpenAI published a hazard analysis framework specifically targeting code synthesis LLMs, addressing the safety and risk dimensions of models that generate executable code. The framework likely identifies threat categories, failure modes, and mitigation strategies relevant to deploying code-generating AI systems. This represents an early structured attempt to apply safety engineering methodology to a specific LLM capability domain. The work is relevant to both AI safety research and enterprise deployment considerations for coding assistants.