Safety-Nudges Chrome Extension Prompts Reflection During AI Chatbot Use
Think of it as a complementary "second pair of eyes”. The goal is to restore user agency and foster AI literacy, by making subtle interaction patterns visible at the exact moment you're most likely to just trust and move on.
Chhavi Yadav@chhaviyadav_We built Safety-Nudges, a lightweight intervention layer, designed to promote awareness & reflection while using LLM chatbots. We chat with AI bots every day now. But there’s a growing problem not talked about enough: People are starting to overtrust AI chatbots. Especially users outside tech. When a chatbot sounds confident, empathetic, and fluent, it’s easy to forget: it can still be wrong, biased, manipulative, or misleading. So here comes Safety-Nudges! https://open-reflection.com
We use a principled taxonomy of harms to identify patterns such as : overconfidence , manipulation, anthropomorphization, emotional steering and misleading framing. Then we provide contextual, real-time flags directly in the interface.
Chhavi Yadav@chhaviyadav_Think of it as a complementary "second pair of eyes”. The goal is to restore user agency and foster AI literacy, by making subtle interaction patterns visible at the exact moment you're most likely to just trust and move on.
The alpha version of Safety Nudges is now available on the Chrome Web Store! To download visit http://bit.ly/safety-nudges & Sign up with the form here (https://open-reflection.com/#install ) to receive an activation code, which allows free Safety-Nudges usage up to $5 in LLM provider credits!
Help us improve Safety-Nudges by providing feedback at openreflection1@gmail.com & optionally sharing annotated interactions while you use the tool!
Chhavi Yadav@chhaviyadav_Our broader goal with Safety Nudges is restoring user agency. Making hidden interaction patterns visible. Helping users recognize when a system may be: • sounding more certain than it should • encouraging emotional dependence • presenting probabilistic outputs as truth