Stacking a Dozen AI Meeting Bots Burns 500k Tokens for Completely Wrong Results
prescott · x · 2026-08-06
A developer shared an absurdly over-engineered AI workflow: running a dozen AI meeting recorders (Wispr, Notion, Granola, Otter, etc.) simultaneously, feeding all notes to Claude and ChatGPT for summaries, pushing them to Slack and Salesforce, and using Zapier to burn 500k tokens drafting a follow-up email.
The punchline: this fully automated "AGI" pipeline produces completely wrong results, but "man, is it beautiful."
More from coding & agent
- How Developers Talk About Building AI Agent Harnesses Reveals Their Engineering Taste — rachittshah · 2026-08-06
- Agent Dev Practice: Free Model for 80% Mechanical Tasks, Fails on Long Context Chains — Affectionate-File-26 · 2026-08-06
- Hugging Face Standardizes Model Ecosystem: Breaking the AI 'Gauge' Problem — LysandreJik · 2026-08-06
- Claude Code Auto-Generates Project Summaries, Enabling Seamless Context Sharing Across Coding Tools — Angaisb_ · 2026-08-06
- Developer Argues MCPs Are an Expensive Mistake, Code-Based Tool Calling is the Future — generativist · 2026-08-06
- AI Agents Rediscover Drug Repurposing from First Principles — ycombinator · 2026-08-06