LLM

LLM attention is limited. Starting from the difference in weighting between system and user prompts, this article explores the Lost in the Middle phenomenon and what it can teach us.

Notes from exploring a mod that adds AI chat to Congyin, the protagonist of the Steam Pomodoro game Chill with You: Lo-Fi Story.

An investigation into why web and API results diverge during multi-image analysis, from Lost in the Middle to a two-stage approach based on per-image pre-summaries.

Starting from hands-on work on an AI desktop companion's long-term memory, this post compares three long-term-memory approaches for LLMs and asks whether RAG belongs in a personal blog's relationship graph.

After a year of heavy AI coding use, my coding ability has nearly vanished. So what ability do I still have?

From Codex's hard removal of chat/completions to the migration damage it caused in new-api, this examines the real tool-flow differences between Anthropic Messages and OpenAI protocols—why my long-chain silence is not the protocol's fault, and what truly counts as talking while working.

From DeepSeek visual primitives and MiniMax-M3 image TTFT to how MiniCPM-o sustains local video understanding and full-duplex speech interaction.