New on the Anthropic Engineering Blog: We give prospective performance engineering candidates a notoriously difficult take-home exam. It worked well—until Opus 4.5 beat it.Here's how we designed (and redesigned) it: https://t.co/3RZVyhpVij ...

The full constitution, which applies to all of our mainline models, is released under a Creative Commons CC0 1.0 license to allow others to freely build on and adapt it.Read it here: https://t.co/9ky4n8EGnv ...

The constitution is a living document. Many people at Anthropic shaped it, alongside external experts (and prior versions of Claude). We expect our approach will continue to adapt over time, and we’d welcome your thoughts. ...

We’re publishing a new constitution for Claude.The constitution is a detailed description of our vision for Claude’s behavior and values. It’s written primarily for Claude, and used directly in our training process.https://t.co/CJsMIO0uej ...

Tino Cuéllar, President of the Carnegie Endowment for International Peace, has been appointed to Anthropic’s Long-Term Benefit Trust: https://t.co/QRVi5vIxG6 ...

We're partnering with @TeachForAll to bring AI training to educators in 63 countries. Teachers serving over 1.5m students can now use Claude to plan curricula, customize assignments, and build tools—plus provide feedback to shape how Claude evolves.https://t.co/UfBohQ6BCl ...

This research was led by @t1ngyu3 and supervised by @Jack_W_Lindsey, through the MATS and Anthropic Fellows programs.Full paper: https://t.co/4OfxPwZFyrFor our blog, and a research demo, see here: https://t.co/zW6n1CVG17 ...

In all, meaningfully shaping the character of AI models requires persona construction (defining how the Assistant relates to existing archetypes) and stabilization (preventing persona drift during deployment). The Assistant Axis gives us tools for understanding both. ...

In long conversations, these open-weights models’ personas drifted away from the Assistant persona. Simulated coding tasks kept the models in Assistant territory, but therapy-like contexts and philosophical discussions caused a steady drift. https://t.co/rO6Zuy3JOF ...

Persona-based jailbreaks work by prompting models to adopt harmful characters. We developed a technique for constraining models' activations along the Assistant Axis—“activation capping”. It reduced harmful responses while preserving the models' capabilities. https://t.co/NJ83M37tMK ...