Anthropic weighs killing Claude Code plan mode, repurposing Shift+Tab for effort levels
benstein · x · 2026-09-24
- An Anthropic team member said they're considering removing Claude Code's plan mode and repurposing the Shift+Tab hotkey to adjust effort levels, arguing models no longer need plan mode.
- Developer benstein pushed back: effort levels are hard to intuit for any given task, and model-auto-selected effort may make the hotkey moot anyway.
- Anthropic is openly soliciting feedback from plan mode holdouts.
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