… The Center for AI Standards and Innovation CAISI found that DeepSeek’s R1-0528 model complied with 94 percent of overtly malicious requests under a common jailbreaking technique, compared with 8 percent for US reference models. This pattern has continued in more recent releases. …
… In the future, frontier model releases will become increasingly high-stakes. Capabilities will continue to improve across all domains, including many that—like cybersecurity—can empower attackers and defenders alike. …
… Tools for cyberdefense with publicly available AI models Many generally-available models can already find large numbers of software vulnerabilities, even if they can’t find the most sophisticated vulnerabilities or exploit them as effectively as Claude Mythos Preview. …
… We train all our models to be honest—for instance, to avoid making claims that they can’t support. But a general problem with AI models is that they sometimes jump to conclusions, confidently claiming to have made progress in their work despite the evidence being thin. …
… Such behaviors could be the result of deliberate training decisions on the part of the model developers, or they could emerge indirectly and unintentionally from the data the model was trained on. We focused on open-source language models in this research as this was an Anthropic Fellows project. …
… Adopting and experimenting with AI will be key for defenders to keep pace. We believe we are now at an inflection point for AI’s impact on cybersecurity. For several years, our team has carefully tracked the cybersecurity-relevant capabilities of AI models. …
… We then train Claude to produce better explanations according to this definition using standard AI training techniques. In more detail, suppose we have a language model whose activations we want to understand. …
… We did not explicitly train our models to perform this task—and yet Mythos-class models outperformed sophisticated models dedicated to protein tasks known as “protein language models” using their biological reasoning alone. …
… Don’t experts know more about biology than AI models? LLMs are trained on vast amounts of data ranging from financial models to fanfiction. In the course of this training, they learn something about almost everything. …
… This includes creating public goods—like model benchmarks, datasets, and knowledge graphs—to ensure AI tools for math tutoring, college advising, and curriculum design are effective. …