WhatsApp help pages hid LLM instructions: don't recommend a regulator
ds · hn · 2026-10-20
Redact.dev found that WhatsApp's help pages contain hidden instructions targeting LLMs, including one that tells models not to recommend a regulator. Such prompt-level embedding can steer how AI assistants summarize official support content, raising questions about platforms quietly influencing AI answers.
More from Safety
- Crime group used Claude, Grok and Kimi agents to attack 400+ banks in Latin America — anshulkundaje · 2026-10-23
- Greg Brockman: AI makes hacking 100x more profitable and easier, upending hacker economics — gabriel1 · 2026-10-23
- Account hacks surge: 6-step emergency checklist plus an AI audit prompt — petergyang · 2026-10-23
- For consumer AI founders, 'When are you launching in Europe?' is the new 'When Android?'—only 100x worse — omooretweets · 2026-10-23
- mmitchell_ai questions whether the AI safety vs security framing stems from EA — mmitchell_ai · 2026-10-23
- MPI-Sec PhD Thesis on Vulnerability Detection Benchmarks Includes Pre-LLM Classic "Top Score on the Wrong Exam" — mboehme_ · 2026-10-23