#alignment — Claude Updates

Video

Anthropic just published a model card for a model they're NOT releasing. This has NEVER happened before. Claude Mythos is the most capable...

Watch

IndyDevDan 0 0

Video

Learn what AI researchers mean when they talk about sycophancy, when it's more likely to show up in conversations, and tactics you can use t...

Watch

Anthropic 0 0

Claude Skill 734

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

Python Apache-2.0 Updated 1w ago

agentscope-ai 0 0

MCP Server 279

A native policy enforcement layer for AI coding agents. Built on OPA/Rego.

Rust Apache-2.0 Updated 4mos ago

eqtylab 0 0

MCP Server 4

DPO/SafeDPO/OPAD training + eval for teaching tool-using LLMs to refuse falsely-benign MCP exploits

Python Apache-2.0 Updated 1w ago

johnhalloran321 0 0

MCP Server 7

Agent Alignment Protocol — the missing trust layer for the agent stack

Python Apache-2.0 Updated 1w ago

mnemom 0 0