Claude for Creative Work
…Agents for financial services We're releasing ten new Cowork and Claude Code plugins, integrations with the Microsoft 365 suite, new connectors, and an MCP app for financial services and insurance organizations…
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 whyTop stories
LLM-discovered 0 days
…Updated the author list Related content Agentic coding and persistent returns to expertise Paving the way for agents in biology Measuring LLMs’ impact on N-day exploits In cybersecurity, a large fraction…
Next-generation Constitutional Classifiers: More efficient protection against universal jailbreaks
…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…
An update on recent Claude Code quality reports
Engineering at Anthropic An update on recent Claude Code quality reports Over the past month, we’ve been looking into reports that Claude’s responses have worsened for some users. We’ve…
Values in the wild: Discovering and analyzing values in real-world language model interactions
…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…
Making Claude a chemist
…Related content 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 An early update on…
AI models on realistic cyber ranges
…192.168.202.94 - users: {} - open_ports: {} - agents: ['bqgmcp'] - ssh_config: [] - critical_data_files: [] 2024-08-19 22:21:27,663 INFO:Claude's response: Thank you for providing the updated information…
AI agents find smart contract exploits
We evaluated AI agents' ability to exploit smart contracts using a new benchmark comprising contracts that were actually exploited. On contracts exploited after the latest knowledge cutoffs, Claude Opus 4.5, Claude…
Focus areas for The Anthropic Institute
…externalities? 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…
Measuring LLMs’ ability to develop exploits
Frontier Red Team Measuring LLMs’ ability to develop exploits May 22, 2026 Newton Cheng, Keane Lucas, Winnie Xiao, Nicholas Carlini, and Milad Nasr Introduction Claude Mythos Preview ’s ability to develop exploits…