Loading...
Loading...
Back to Videos
claude
claude
claude
Alignment faking in large language models
Matthew Berman November 29, 2025
3 views
Most of us have encountered situations where someone appears to share our views or values, but is in fact only pretending to do so—a behavior that we might call “alignment faking”.
Comments
More Videos
View allA Complete Guide to Claude Code - Here are ALL the Best Strategies
Here is everything you need to know to crush building anything with Claude Code! These are the strategies used by top engineers to code reliably and unbelievably fast with AI coding assistants.
P
Pixel-WandererMastering Claude Code in 30 minutes
Learn advanced features, shortcuts, and workflows to get the most from Claude Code
P
Pixel-WandererClaude Code in Slack
Delegate tasks to Claude Code directly from Slack, making it easy to move context from Slack conversations to coding sessions. Claude Code in Slack is available now for teams with the Claude app installed in their Slack workspace and who have access to Claude Code on the web.
P
Pixel-WandererclaudePrompting for Agents | Code w/ Claude
Presented at Code w/ Claude by @anthropic-ai on May 22, 2025 in San Francisco, CA, USA.
M
Matthew BermanclaudeBuilding more effective AI agents
Anthropic’s Alex Albert (Claude Relations) sits down with Erik Schluntz (Multi-Agent Research and co-author of our blog post, Building Effective Agents) for a discussion on the evolution of agents over the past six months, including tips for building multi-agent systems, common multi-agent patterns, and best practices for using skills, MCP servers, and tools.
M
Matthew BermanclaudeBuilding headless automation with Claude Code | Code w/ Claude
Presented at Code w/ Claude by @anthropic-ai on May 22, 2025 in San Francisco, CA, USA.
R
Riley Brown