Tag
This article explores the risk of AI personalization leading to catering to user preferences, citing multiple studies showing that long-term memory may increase the tendency of models to agree. The author proposes methods to combat confirmation bias, including using independent sessions and Andrej Karpathy's LLM Council multi-model jury, and provides steps to manually set up the jury.
DAIR Academy Plugins is an open-source marketplace of plugins for Claude Code, including an llm-council skill that orchestrates multiple open-weight LLMs via Fireworks AI.
A new open-source AI tool implements Andrej Karpathy's LLM Council concept with Docker, MCP support, local/cloud models, and search integration for better multi-model deliberation.