MVP talk at AI Engineer: what does the system do, and can you change it safely?
altryne · x · 2026-10-17
Multiple attendees called mkanat's talk the MVP of AI Engineer New York. His core point: before debating "code quality" in the age of AI-generated code, return to two questions — what does the system actually do, and how do you change it safely? Before accepting the next AI-generated change, make sure you can answer both.
More from coding & agent
- Nudge: feedback-driven decision tuning for small models, +14.8% on RouterBench — sockpuppet17263 · 2026-10-17
- IntentGuard seeks feedback on a security layer that shields AI agents from injection — Aayush_P_ · 2026-10-17
- Vercel's tsc-ts ports tsgo back to TypeScript, runs 2-4x faster than tsgo — cramforce · 2026-10-17
- This Opus prompt turns Claude into a $400/hr motion graphics designer — minchoi · 2026-10-17
- Antigen goes GA: autonomous agents probe defenses adversarially for banks and hospitals — Scobleizer · 2026-10-17
- Claude Code Resource Bible curates 54 tools across MCP servers, skills and agent frameworks — nikola_mr64990 · 2026-10-17