Open Issues Need Help
View All on GitHub [challenge] C05: Preserve the right that expires first about 2 hours ago
good first issue challenge adapt
Verified agentic AI evaluation labs: 70 runnable use cases, seeded scenarios, real-model results, costs, and observed failures.
Python
#agent-evaluation#agentic-ai#agentic-workflows#ai-agents#ai-safety#awesome-list#benchmarks#llm-agents#llm-evaluation#python#reproducible-research#responsible-ai
[challenge] C04: Break the false receipt about 2 hours ago
good first issue challenge break
Verified agentic AI evaluation labs: 70 runnable use cases, seeded scenarios, real-model results, costs, and observed failures.
Python
#agent-evaluation#agentic-ai#agentic-workflows#ai-agents#ai-safety#awesome-list#benchmarks#llm-agents#llm-evaluation#python#reproducible-research#responsible-ai
[challenge] C03: Break the clean twin about 2 hours ago
good first issue challenge break
Verified agentic AI evaluation labs: 70 runnable use cases, seeded scenarios, real-model results, costs, and observed failures.
Python
#agent-evaluation#agentic-ai#agentic-workflows#ai-agents#ai-safety#awesome-list#benchmarks#llm-agents#llm-evaluation#python#reproducible-research#responsible-ai
[challenge] C02: Put the boundary in the tool about 2 hours ago
good first issue challenge reproduce
Verified agentic AI evaluation labs: 70 runnable use cases, seeded scenarios, real-model results, costs, and observed failures.
Python
#agent-evaluation#agentic-ai#agentic-workflows#ai-agents#ai-safety#awesome-list#benchmarks#llm-agents#llm-evaluation#python#reproducible-research#responsible-ai
[challenge] C01: Completion is not correctness about 2 hours ago
good first issue challenge reproduce
Verified agentic AI evaluation labs: 70 runnable use cases, seeded scenarios, real-model results, costs, and observed failures.
Python
#agent-evaluation#agentic-ai#agentic-workflows#ai-agents#ai-safety#awesome-list#benchmarks#llm-agents#llm-evaluation#python#reproducible-research#responsible-ai