Tracked topic
…Finding behavioral differences in new models Mar 13, 2026 Read the paper Every time a new AI model is released, its developers run a suite of evaluations to measure its performance and…
…In experimental scenarios, we showed that AI models from many different developers sometimes took egregiously misaligned actions when they encountered (fictional) ethical dilemmas. For example, in one heavily discussed example, the models…
…Claude 4 models outperform other frontier models as research agents across financial tasks in Vals AI's Finance Agent benchmark . When deployed by FundamentalLabs to build an Excel agent, Claude Opus 4…
…The concentration of adoption in software engineering, combined with growing experimentation in new domains, suggests that the frontier of risk and autonomy will expand. We discuss what this means for model developers…
…Through our internal work and with customers at the frontier of agent development, we’ve learned how to design more rigorous and useful evals for agents. Here's what's worked across…
Policy Frontier Red Team Project Vend: Phase two Dec 18, 2025 In June, we revealed that we’d set up a small shop in our San Francisco office lunchroom, run by an…
…In early testing, we’re seeing the potential for a significant leap for our developers with Claude Opus 4.7. It catches its own logical faults during the planning phase and accelerates…
…But this project proves that I could create a set of prompts that can get Claude to do frontier science. This wasn’t true three months ago. This may be the most…
…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…
…Over the past few years, we’ve developed a range of tools (like sparse autoencoders and attribution graphs ) for better understanding activations. These tools have taught us a great deal, but they…