Why fully agentic development is unsolvable: intent is fractal, latent, dynamic
RexDouglass · x · 2026-10-20
Applied scientist Rex Douglass is job hunting (remote, full-time or projects), sharing 33 projects spanning machine vision, agents/LLM, forecasting and GIS. His core thesis on agentic development: user intent is fractal, latent, and dynamic, and agent performance is unverifiable—the more you delegate, the less you can check.
Related event: Researcher Argues Fully Delegating to Agents Is Mathematically Impossible(4 posts)→
More from coding & agent
- Cua launches Spaces SDK to run Claude Code and any agent on compute you choose — Scobleizer · 2026-10-20
- Dev: top AI agents do more backup and verification on DB migrations than 99.99% of engineers — tristanbob · 2026-10-20
- 20 questions to answer before letting agents touch production data — Then_Respect_1964 · 2026-10-20
- Baseten webinar: how to evaluate open models for coding agents on your own codebase — baseten · 2026-10-20
- Every's Slack agent turns article links into videos with a storyboard-first workflow — every · 2026-10-20
- Don't be a meat proxy for your agent — make it a metal proxy for you — danshipper · 2026-10-20