2026
-
Talk with Shunyu Yao: feedback is the center of AI research
TLDR: The conversation is useful because it frames AI research as system-driven experimental work: define verifiable problems, build feedback loops, debug carefully, and choose directions where scaling paths are still being shaped.
-
Anthropic Blogs: harness engineering and context engineering
The shared lesson across these Anthropic engineering posts is that long agent tasks fail at the runtime layer: context, evaluation, sandboxing, permissions, handoff, and feedback have to be engineered.
-
Building a C compiler with agent teams
The C compiler experiment worked because the project had the right substrate for agents: a modular architecture, objective tests, Git as shared memory, task locks, readable logs, and oracles that turned one giant goal into many local failures.
-
Claude Code Auto Mode: permissions as runtime safety
Claude Code auto mode is not just fewer confirmation prompts. It is a runtime safety design that separates low-risk actions, intent-aware classification, prompt-injection defenses, and recovery after denial.
-
Claude Code Source: an agent as an operating-system process
Reading Claude Code through an operating-system lens makes the agent runtime concrete: context preparation, tools, permissions, subprocesses, cancellation, compaction, plugins, and exit paths.