"I hate running 15 agents": developers push back on parallel agent workflows
bradneuberg · x · 2026-10-29
A relatable rant sparked a debate on current multi-agent coding culture: the original poster admits hating running 15 agents at once and the constant context-switching, missing going deep on things. Brad Neuberg's response offers an alternative: you can just decide not to go wide with your agents — do less and go deeper. Everyone is choosing velocity, but you can choose quality and actual comprehension of what you produce. The thread captures an emerging split between parallel-agent throughput and depth/quality in AI-assisted engineering.
More from coding & agent
- Evals: The Most Underrated Skill in AI Engineering, From Error Analysis to Versioned Golden Datasets — sudoraohacker · 2026-10-29
- Deep dive: editing videos with Claude Code and Opus 5.5, from prompts to a 31K-view short — aakashgupta · 2026-10-29
- This creator spent 40 hours turning Claude into a video editor — and published the full free harness — aakashgupta · 2026-10-29
- Reading PRs through behavior tests: green lines mean additions, red lines mean changes — samgoodwin89 · 2026-10-29
- spawn: 10-person company spends 30x payroll on AI tokens, ships like Anthropic — Scobleizer · 2026-10-29
- SQL hidden in a string literal bypasses LLM-to-SQL gates; schemagate 1.15.1 fixes it — Temporary_Papaya1058 · 2026-10-29