iMessage AI agent showdown: only Instinct fully completes a flower-buying task
msg · x · 2026-10-16
David Pawlan tested multiple iMessage AI assistants with the same prompt ("buy me the cheapest flowers, guest checkout, same-day delivery, no questions") to probe search quality and end-to-end purchase ability:
- 🥇 Instinct: fastest to find the cheapest option and completed the purchase
- 🥈 thesznai: completed the purchase
- 🥉 kickerai: bought via Amazon but required installing a Chrome extension for browser use
The post also promotes msgblast, an open-source Mac app that sends one prompt to multiple AI agents (apps, iMessage bots, local CLIs like Codex CLI and Claude Code) to compare their answers side by side.
More from coding & agent
- Bash's hidden /dev/tcp stack lets you make raw TCP calls without curl or netcat — RealGeneKim · 2026-10-16
- dair-ai explores context graphs for research tasks: LLM agents love structured data — omarsar0 · 2026-10-16
- Codex CLI v0.163.0 adds mid-response steering, parallel read-only tools and /config search — github-actions[bot] · 2026-10-16
- Hooking Codex CLI into Claude spawns a four-subagent "council" for any question — RosieCampbell · 2026-10-16
- AI-optimized MACS3 merged: 41-64x callpeak speedup via Claude Code, human-reviewed — jmschreiber91 · 2026-10-16
- Prompt extracted from Anthropic eng lead's tutorial: make Claude push you to be more ambitious first — kieranklaassen · 2026-10-16