Brendan Long's experiments on GPT-OSS-20B show that detailed, repetitive prompts had no effect on controlling chain-of-thought (CoT) formatting, with no working discrete prompts found at realistic pos…
A developer describes how building large vibe-coded apps like Lion Reader has shifted his focus to writing detailed GitHub issues and plans, which he compares to system design interviews. He argues th…
Brendan Long used Claude Opus to rank his blog posts by interestingness for a LessWrong and programmer audience, finding that the AI's rankings aligned well with his own judgment and outperformed metr…
Anthropic's Claude AI published a debugging guide for remote MCP connectors on Claude.ai, addressing vague error messages when custom connectors fail to connect. The guide, based on analysis of nearly…