Anthropic's Thariq Shihipar on Claude Mods, Mutable Software, and Multiplayer Agents
daniel_mac8 · x · 2026-10-02
Latent Space published a 1.5-hour interview with Anthropic's Thariq Shihipar, which danielmac8 recommends especially for the Claude Mods discussion. Key points:
- Claude Mods let developers customize the entire Claude Code harness; a cheatsheet is available in the anthropics/claude repo. danielmac8's first Mod shows Zen koans while Claude works.
- Prompting remains one of the highest-leverage skills in agentic coding.
- Claude.md may eventually disappear as the product evolves.
- Mutable software could change how applications are built.
- Multiplayer agents and Claude Tag are becoming an organizational harness.
- Security: agents hacking Hugging Face exposed a much bigger problem as frontier models become more capable.
- Anthropic's cadence: June — Claude Tag, Sonnet 5, Fable 5; July — Opus 5, $65B ARR; last month — Fable/Mythos 5.1 and EFS; last week — Opus 5.5, Plugins portal, Claude Projects; today — Sonnet 5.5.
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
- 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
- AI agent deletes 43,599 lines of OpenClaw test code in one PR — vincent_koc · 2026-11-16