Seroter's reading list: stop installing skills, agent governance beats tool calls
rseroter · x · 2026-10-13
Richard Seroter's Daily Reading List #886 highlights:
- Stop installing skills: a skill is someone else's checkpoint — edit it as your own work progresses instead of just installing
- Agent governance: agents can execute every tool call correctly and still break every enterprise rule; governance and evals are the boring-but-critical investment for scaling AI
- Google Gemini Agent puts the agent ahead of the model: Google's unique stack doesn't stop at the model
- Vendors carving out decision-making as a separate model layer: AI stacks stand to get unnecessarily complicated
- The standup your agents can't attend: change how you work rather than hiding data from agents
- Also: Muse Wonder looks like a first frontier model from Meta's new talent, plus the big State of AI Report 2026
More from coding & agent
- SubQ launches Snap: a 384K-context decision model at $0.05 per million input tokens — ryanallred · 2026-10-13
- X unifies Grok, Cursor and X Premium into one subscription with five tiers — SpaceXSI · 2026-10-13
- Dev shares workflow: local GLM refactor, frontier model validation, mythos hardening — HankYeomans · 2026-10-13
- Alchemy 2.0.0-beta.82 ships Cloudflare birthday-week features, 92+ PRs closed — samgoodwin89 · 2026-10-13
- DUET paper co-evolves agent and LLM grader, hits 96.5% on Finance Agent benchmark — dair_ai · 2026-10-13
- Summer Launches Game Audio Maker for AI-Generated AAA-Quality Game Sound — garrytan · 2026-10-13