Claude Code and What Comes Next
- Source
- oneusefulthing.org
- Author
- Ethan Mollick
- Date
A clear, concrete walkthrough of how agentic coding harnesses actually work — , Skills, subagents, and — in a real 74-minute autonomous build-and-deploy run, useful for anyone trying to understand or push the limits of long-horizon coding agents.
- context compaction — Summarizing an agent's earlier conversation to free room in the context window so a long session can keep going.
- MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
- LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
- grounding — Tying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.
“I strongly suspect that if I ignored my conscience and actually sold these prompt packs, I would make the promised $1,000.”
“What makes these new tools suddenly powerful is not one breakthrough, but a combination of two advances.”
“But there's a deeper point here: with the right harness, today's AIs are capable of real, sustained work that actually matters, and that, in turn, is starting to change how we approach tasks.”
“The profession is being dramatically refactored as the bits contributed by the programmer are increasingly sparse and between.”
Andrej Karpathy
“New harnesses that make AI work for other knowledge tasks are coming in the near future, and so are the changes that they will bring.”
Checking sign-in…
Loading comments…