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.
Related event: Anthropic Engineer Discusses Claude Code's Future on Latent Space(2 posts)→
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- Effective HTML: 4.2k-star agent skills turn wireframes into self-contained interactive prototypes — tom_doerr · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16