Should agents internalize the loop, or keep enforcement outside?
DanielKhashabi · x · 2026-07-21
A thread argues that the next step after reasoning models and learned tool use is to **internalize the agent loop itself**. The proposed direction is for models to own planning, tool use, error recovery, verification, memory, and stopping decisions—possibly even tool design and skill composition. But the author draws a hard boundary: the model should handle cognition, while the harness still provides sandboxing, permissions, budgets, and auditing as an enforcement layer that does not trust the policy. The core question is where that boundary should sit, and how to distinguish true internalization from superficial tool-form behavior.
More from coding & agent
- Cross-agent system logs are dominated by questions and code proposals — nptacek · 2026-07-21
- Coding agents need better rules for when to read search summaries or full pages — RhubarbLarge2747 · 2026-07-21
- Chart compares open tickets across Gemini, Codex, Claude, Grok and Opus 3 — nptacek · 2026-07-21
- Notch says he may try vibe coding after struggling to hire good programmers — max_paperclips · 2026-07-21
- Seedance 2.0 keeps character consistency across 15+ shots with just 3 prompts — techhalla · 2026-07-21
- Measuring hung AI coding agents automatically with per-project time and token accounting — VCBU · 2026-07-21