LLMs and biorisk
… Footnotes 1 This is based on a review of the published safety frameworks collected by METR at https://metr.org/faisc as of July 2025. …
Search
People also ask
What safety risks?
If you’re willing to entertain the views outlined above, then it’s not very hard to argue that AI could be a risk to our safety and security. There are two common sense reasons to be concerned. First, it may be tricky to build safe, reliable, and steerable systems when those systems are starting to become as intelligent and as aware of their surroundings as their designers. To use an analogy, it is easy for a chess grandmaster to detect bad moves in a novice but very hard for a novice to detect bad moves in a grandmaster. If we build an AI system that’s significantly more competent than human
Core views on AI safety: When, why, what, and howCore views on AI safety: When, why, what, and how
… The role of frontier models in empirical safety A major reason Anthropic exists as an organization is that we believe it's necessary to do safety research on "frontier" AI systems. This requires an institution which can both work with large models and prioritize safety 5 . …
Anthropic commits $10 million to Canadian AI research
… Today, Canadians both at home and abroad continue to play leading roles in AI research, safety, and policy—including at Anthropic. …
Claude Code auto mode: a safer way to skip permissions
… Safety-check bypass . …
Quantifying infrastructure noise in agentic coding evals
… Until resource methodology is standardized, our data suggests that leaderboard differences below 3 percentage points deserve skepticism until the eval configuration is documented and matched. …
Patterns and problems in multiagent systems
… Our world contains deceptive actors, and we need to apply skepticism to guard against them. …
Harness design for long-running application development
…But tuning a standalone evaluator to be skeptical turns out to be far more tractable than making a generator critical of its own work, and once that external feedback exists, the generator…