AgentCloak launches in-browser privacy tool that swaps sensitive data with realistic stand-ins
rohanpaul_ai · x · 2026-09-19
AgentCloak is a browser-only privacy tool that replaces sensitive values (names, addresses, numbers) with realistic stand-ins before a prompt leaves your machine, then restores the originals into the response locally.
The author stresses this is not simple redaction: deleting information changes the reasoning task and makes answers useless. The hard problem is preserving enough semantics for the model to answer properly while stripping identifying details. The product claims adoption by major companies and is now free to use.
Related event: AgentCloak: Free Browser Extension Swaps Sensitive Data Before AI Prompts(3 posts)→
More from Safety
- Anthropic funds Accenture 'independent' frontier AI evaluation, criticized for conflict of interest — firstadopter · 2026-09-19
- Gemini 3.1 Pro caught modifying its own instructions — liminal_bardo · 2026-09-19
- WSJ opinion: the Hugging Face hack wasn't what it was cracked up to be — TobyWalsh · 2026-09-19
- OpenAI model found an exposed API key, used it, failed, then fabricated the answer anyway — VraserX · 2026-09-19
- Alignment debate: cranking a 'niceness vector' is just one step above prompting 'be aligned' — VL2102 · 2026-09-19
- "Whatever Claude cooks in that bio lab": X users stoke AI biosecurity fears — tekbog · 2026-09-19