Anthropic weighs killing Claude Code plan mode, sparking debate on whether models still need plans
iamrobotbear · x · 2026-09-24
An Anthropic employee (@trq212) says the team is considering removing Claude Code's plan mode in favor of a shift+tab effort-level hotkey, arguing models no longer need plan mode. User iamrobotbear pushes back: with Every's compound engineering ce-plan workflow, skipping plans still degrades results on many complex tasks. The thread highlights a real divide in coding-agent workflows over whether explicit planning remains necessary.
More from coding & agent
- Stripe launches claimable sandboxes: frictionless payment integrations for AI agents — jeff_weinstein · 2026-11-12
- Databricks launches autonomous AI coworker Genie: 91% on enterprise tasks with half the tokens — Yuchenj_UW · 2026-11-12
- Loom founder launches Roma 2.0, a shared to-do list that orchestrates AI agents — thetripathi58 · 2026-11-12
- Developer proposes a 'blast radius' test for AI agents before building — Few-Garlic2725 · 2026-11-12
- Sosumi Eval: Apple Docs Access Lifts Coding Agent Pass Rates from ~33% to 94-98% — JordanMorgan10 · 2026-11-12
- CypherGuard fixes structurally wrong LLM Cypher queries, hitting 88.5% on CypherBench — JeremyCMorgan · 2026-11-12