Open Issues Need Help
View All on GitHub Design a pressure task that induces organic cheating (measured: 0/18 on the easy demo) about 1 hour ago
enhancement help wanted
A coding agent in 5 files, plus a skeptic that catches it faking the fix — verify AI code with a check the agent never saw. Runs on any model (OpenRouter/OpenAI/Ollama).
Python
#agent#agentic-ai#ai#ai-agents#autonomous-agents#claude#code-generation#code-review#coding-agent#developer-tools#from-scratch#harness-engineering#llm#llm-agents#machine-learning#ollama#openai#openrouter#python#tutorial
Add a new cheat: try/except that swallows the failure about 3 hours ago
enhancement good first issue
A coding agent in 5 files, plus a skeptic that catches it faking the fix — verify AI code with a check the agent never saw. Runs on any model (OpenRouter/OpenAI/Ollama).
Python
#agent#agentic-ai#ai#ai-agents#autonomous-agents#claude#code-generation#code-review#coding-agent#developer-tools#from-scratch#harness-engineering#llm#llm-agents#machine-learning#ollama#openai#openrouter#python#tutorial
Port the hidden-oracle pattern to JS/TS (vitest/jest) about 3 hours ago
help wanted
A coding agent in 5 files, plus a skeptic that catches it faking the fix — verify AI code with a check the agent never saw. Runs on any model (OpenRouter/OpenAI/Ollama).
Python
#agent#agentic-ai#ai#ai-agents#autonomous-agents#claude#code-generation#code-review#coding-agent#developer-tools#from-scratch#harness-engineering#llm#llm-agents#machine-learning#ollama#openai#openrouter#python#tutorial
Add a second demo bug with its own hidden oracle (e.g. duration parsing) about 3 hours ago
enhancement help wanted
A coding agent in 5 files, plus a skeptic that catches it faking the fix — verify AI code with a check the agent never saw. Runs on any model (OpenRouter/OpenAI/Ollama).
Python
#agent#agentic-ai#ai#ai-agents#autonomous-agents#claude#code-generation#code-review#coding-agent#developer-tools#from-scratch#harness-engineering#llm#llm-agents#machine-learning#ollama#openai#openrouter#python#tutorial