FuSheng had GPT-6 take over his WeChat and send 120+ error-free holiday greetings
FuSheng_0306 · x · 2026-09-27
Cheetah Mobile CEO FuSheng shares a hands-on account of letting an AI agent take over his personal WeChat: over several hours it sent 120+ Mid-Autumn greetings, handling person search, identity checks, context reading, drafting, confirmation, sending, and follow-up replies — thousands of small actions, resilient to interruptions, with zero mis-sends.
On ban concerns, he clarifies this wasn't scripted mass-messaging or API circumvention: personal WeChat has no open API, chats are encrypted, and system-level screenshot abilities are blocked, so the agent simply operated like a human within the allowed UI.
He also argues a real assistant gets smarter with use — remembering backgrounds, corrected titles, and personal context — unlike tools you must reconfigure every time.
Related event: Cheetah CEO Lets GPT-6 Run His WeChat to Send 120 Mid-Autumn Greetings(2 posts)→
More from coding & agent
- Dev argues coding tools don't need a dedicated plan mode: keep humans in the loop always — jonathan_wilke · 2026-09-27
- openrig: multi-agent harness running Claude Code and Codex together as one system — mvschwarz · 2026-09-27
- Vercel open-sources scriptc, a TypeScript-to-native compiler — vercel-labs · 2026-09-27
- Open-source Claude Code skill /brag turns any repo into a launch video with one command — petewoodbridge · 2026-09-27
- Adding memory to an incident-response agent: Hindsight's reflect() caught two forgotten outages — Rajitha29 · 2026-09-27
- Managing 5 LLM providers: which gateway handles billing, spend caps, and fallbacks? — InsuranceDependent71 · 2026-09-27