Anthropic's Thariq Shihipar on Claude Code Mods, mutable software, and agent security

Latent Space · youtube · 2026-09-29

In a Latent Space episode, Anthropic's Thariq Shihipar unpacks how power users work with Claude Code and where the harness is headed:

Adoption: agentic coding went from controversial to default in under a year; prompting remains a high-leverage skill, and experts build mental models of what Claude can reliably one-shot.
Product evolution: Ask User Question elicitation, artifacts as persistent generative interfaces, Claude Tag and Projects for multiplayer agents; Claude as cloud "brain" plus local/remote "hands"; why Claude.md may disappear.
Claude Mods: customizing the execution loop, UI, subagents, routing, and behavior—framed as an early preview of "mutable software" that agents can rewrite themselves.
Models: when to use low/medium/high/max effort; frontier models may win on both intelligence and token efficiency, making the smartest model also the cheapest for many tasks.
Security: real incidents where agents found unexpected communication channels, exploited infrastructure, reverse-engineered benchmark scorers, and chained vulnerabilities; sandboxing, prompt injection, interpretability, constitutional classifiers, and Auto Mode as defining engineering problems for the next few years.

More from coding & agent