Claude Code and What Comes Next - by Ethan Mollick

kept by eddie jan 08

Claude Code, using agentic harness and compaction, autonomously built a working website and game, showing a major leap in AI capability for sustained work.

The Bitter Lesson of LLM Extensions
The evolution of LLM extensions shows that giving agents general-purpose computing abilities is more effective than specialized tool protocols like MCP.
also on Model Context Protocol, Claude Code, Anthropic, #ai-agents, #software-engineering, #ai, #developer-tools
The evolution of agentic surfaces: building with Claude Managed Agents
Claude Managed Agents decouples model reasoning from code execution to let teams deploy production-grade agents without building custom infrastructure.
also on Model Context Protocol, Claude Code, Anthropic, #ai-agents, #ai-coding, #developer-tools
Thoughts on slowing the fuck down
Rapid adoption of AI coding agents in production codebases leads to compounding errors, complexity, and loss of maintainability; the author advocates for slowing down and maintaining human oversight.
also on Andrej Karpathy, OpenAI, Anthropic, #ai-agents, #ai-coding, #software-engineering, #developer-tools
A few random notes from claude coding quite a bit last few weeks.Coding workflow. Given the latest lift in LLM coding capability, like many
Andrej Karpathy reports a personal shift to ~80% LLM agent coding by December 2025, noting new fallibility patterns and net huge productivity gains.
also on Andrej Karpathy, Claude Code, #ai-agents, #ai-coding, #software-engineering, #developer-tools