Project Vend: Phase two
…Claudius was required to report back via an agent-to-agent Slack channel we created, in which the models discussed business strategies. Cash took on the role of the CEO with great…
Search
Related topics:
Claude
People also ask
Why does agentic misalignment happen?
Before we started this research, it was not clear where the misaligned behavior was coming from. Our main two hypotheses were: Our post-training process was accidentally encouraging this behavior with misaligned rewards.This behavior was coming from the pre-trained model and our post-training was failing to sufficiently discourage it. We now believe that (2) is largely responsible. Specifically, at the time of Claude 4’s training, the vast majority of our alignment training was standard chat-based Reinforcement Learning from Human Feedback RLHF data that did not include any agentic tool use. T
Teaching Claude whyHarness design for long-running application development
…recent enough that Claude's training data covers it thinly. But with enough tuning, the generator was building agents correctly. Results from the updated harness To put the updated harness to the…
Project Vend: Can Claude run a small shop? (And why does that matter?)
…The shopkeeping AI agent—nicknamed “Claudius” for no particular reason other than to distinguish it from more normal uses of Claude—was an instance of Claude Sonnet 3.7, running for a…
Claude Fable 5 and Claude Mythos 5
…These are the strongest results of any Claude model we've had the opportunity to test. Claude Fable 5 is a clear step forward on agentic coding and prototyping. Claude Fable 5…
Building Effective AI Agents
…When and how to use frameworks There are many frameworks that make agentic systems easier to implement, including: The Claude Agent SDK ; Strands Agents SDK by AWS ; Rivet , a drag and drop…
Donating our open-source alignment tool
…Related content Teaching Claude why New research on how we've reduced agentic misalignment. Natural Language Autoencoders: Turning Claude’s thoughts into text AI models like Claude talk in words but think…
Mapping AI-enabled cyber threats: Insights from the LLM ATT&CK Navigator
…What we learned from this and other analyses directly shapes how we build Claude to prevent such misuse. For example, we’ve updated the classifiers built into Claude to detect the highest…
Anthropic and Amazon expand collaboration for up to 5 gigawatts of new compute
…Updated April 21st to clarify Claude Platform on AWS is coming soon. Related content Higher usage limits for Claude and a compute deal with SpaceX We’ve raised Claude's usage limits…
An update on our election safeguards
Announcements An update on our election safeguards Apr 24, 2026 People around the world turn to Claude for information about political parties, candidates, and the issues at stake during election time—as…
The persona selection model
…Related content Making Claude a chemist Coding agents in the social sciences Results from a survey of 1,260 social scientists about AI and coding agent use. Project Glasswing: An initial update…