Why AI Slop Is So Frustrating to Read, per Zonder Labs
floguo · x · 2026-11-11
Zonder Labs argues LLMs are ironically bad at writing because coding-style capabilities are easier to optimize and monetize. It distinguishes casual social-media slop from workplace slop (AI-flavored Slack messages, PR descriptions) that imposes real cognitive burden, and proposes measuring clarity via strong human agreement as a gold standard, with interactive demos.
More from AGI Musings
- Nine-country study: 51% now use conversational AI, but audiences don't want it making news — _FelixSimon_ · 2026-11-11
- Nat Lambert bets intelligence explosion won't happen before early 2028 — natolambert · 2026-11-11
- RethinkX shuts down research arm after ten years, framing it as a graduation — adam_dorr · 2026-11-11
- Naval: Vibe Coding Is the New Product Management, Model Tuning Is the New Coding — aakashgupta · 2026-11-11
- Kai-Fu Lee: next wave of AI value creation shifts from models to industry applications — kaifulee · 2026-11-11
- Delegating to AI makes price signals more valuable—and crypto more compelling — curious_vii · 2026-11-11