ARCHIVE · 34
Follow the trail from foundational concepts to practical engineering decisions.
OpenAI has launched its new voice model, GPT-Live. If I had to pick one key sentence from the announcement, it would be this: "A full-duplex architecture that listens and speaks simultaneously." No matter how fast previous voice AI became, it was still a walkie-talkie: one side had to finish speaking before the other could respond.…
Read article
In Part 3, we saw how to clear conversation history with /clear. But checking the remaining context immediately afterward shows it is not at 100%. Run /context in Claude Code and the reason becomes clear: the system prompt, tool definitions, CLAUDE.md, and tools registered by MCP servers already consume tens of thousands of tokens…
Read article
When using a coding agent like Claude Code, you may see a warning such as "Context left until auto-compact: 8%" at the bottom of the screen. Chat-based AI does not usually show this. Yet surprisingly few people can explain why the number decreases or what happens when it reaches zero…
Read article
In Part 1, we saw why the context window is finite. But looking at today's model specs raises a question: models with 1 million tokens already exist, so why not just feed in the entire codebase or document? Is there any point in being careful?
Read article
The previous two posts completed the diagnosis. The context window is finite (Part 1), and filling it does not mean everything is used; performance actually declines as it grows (Part 2). The prescription is clear: manage context. Coding agents, including Claude Code, provide /clear and /compact for this purpose…
Read article