Pinned Loading

1. hawk hawk Public

   Forked from METR/hawk

   Run Inspect AI evals in the cloud

   Python

2. inspect_ai inspect_ai Public

   Forked from UKGovernmentBEIS/inspect_ai

   Inspect: A framework for large language model evaluations

   Python

3. monitor-bypass-evals monitor-bypass-evals Public

   Can AI agents find realistic holes in their own monitoring? Sandbox environments modelled on gaps METR found at Anthropic and OpenAI.

   Python 1

4. long-task-cheating-monitors long-task-cheating-monitors Public

   Do LLM monitors catch AI agents that cheat on long tasks? A harness built on Inspect and METR's public tasks.

   Python

5. apache/cloudstack apache/cloudstack Public

   Apache CloudStack is an opensource Infrastructure as a Service (IaaS) cloud computing platform

   Java 3.1k 1.4k

6. simple-coding-agent simple-coding-agent Public

   A simple coding agent

   TypeScript