Item logo image for Safety Nudges

Safety Nudges

Item media 2 (screenshot) for Safety Nudges
Item media 1 (screenshot) for Safety Nudges
Item media 2 (screenshot) for Safety Nudges
Item media 1 (screenshot) for Safety Nudges
Item media 1 (screenshot) for Safety Nudges
Item media 2 (screenshot) for Safety Nudges

Overview

Safety Nudges audits chatbot conversations in real time to screen for common problems.

As AI systems have become widely commercialized and integrated into consumer products, financial and market competition pressures may incentivize companies to promote AI products despite known safety risks or societal harms. Recent incidents and research has raised concerns about potential societal impacts associated with AI use, including overreliance on automated systems, excessive use, persuasive influence, social isolation, and user trust reinforced through sycophantic or overly agreeable responses from AI systems. These safety-related concerns can disproportionately affect vulnerable populations, such as older adults and children. Because the incentives of commercial AI product developers may not always align with broader societal interests, there is a need for independent oversight mechanisms and user-facing tools that can promote awareness of potential risks. Designed by AI safety researchers at Carnegie Mellon University, Safety Nudges provides a low-friction real-time auditing interface for chatbot conversations, restoring agency and awareness to end-users. It checks each conversation turn on ChatGPT and Claude by sending it to an external LLM for review; a principled and comprehensive taxonomy of harms is used to flag the conversation for common pitfalls like flattery, overconfidence, and anthropomorphization. Nudges are integrated gracefully into the chat interface and can be paused at any time. NOTE: Safety Nudges is currently in an alpha release, with codes for free access granted to chosen users. If you do not have a code, you can also provide your own OpenRouter API key. We encourage you to submit feedback to help us improve!

Details

  • Version
    0.1.2
  • Updated
    May 14, 2026
  • Offered by
    james-wedgwood
  • Size
    514KiB
  • Languages
    English
  • Developer
    Carnegie Mellon University
    5000 Forbes Ave Pittsburgh, PA 15213 US
    Email
    jwedgwoo@cs.cmu.edu
  • Non-trader
    This developer has not identified itself as a trader. For consumers in the European Union, please note that consumer rights do not apply to contracts between you and this developer.

Privacy

Manage extensions and learn how they're being used in your organization

Safety Nudges has disclosed the following information regarding the collection and usage of your data. More detailed information can be found in the developer's privacy policy.

Safety Nudges handles the following:

Website content

This developer declares that your data is

  • Not being sold to third parties, outside of the approved use cases
  • Not being used or transferred for purposes that are unrelated to the item's core functionality
  • Not being used or transferred to determine creditworthiness or for lending purposes

Related

No AI

4.6

Extension to block AI Chat bots

RealCustomAI - Auto Long Memory For GPT, Gemini, Grok, Claude

5.0

Conversations are saved in real time, and the AI retrieves relevant past context based on your current input.

al.bot

5.0

Asks your questions to multiple AI chatbots and summarises the answers so you can easily spot mistakes.

AI Safe Chat Guard

5.0

Real-time protection against malicious AI responses, phishing bots, and scams in AI chat interfaces

Clash of LLMs

0.0

Pit AI chatbots against each other in real-time — debates, roasts, interviews, collaborative writing, and more

AI Arena

0.0

Send prompts to ChatGPT, Gemini, and Claude simultaneously with split-screen comparison.

AIChat Voice - AI Voiceover & TTS Assistant for Talkie

0.0

Let AI characters speak with emotion! Provides high-quality real-time voiceover for Talkie.

Gateman - AI Data Loss Prevention

0.0

Prevent data leaks to AI tools. Detects and blocks secrets, API keys, and PII before sending to ChatGPT, Claude, etc.

GuardAI - Privacy Protection for AI Chats

5.0

Detect and mask sensitive info in AI chats. Supports multiple regions and languages for ChatGPT, Claude, Gemini.

Personal Pragatix - Your Free Private Local AI Assistant Chatbot

5.0

Private AI Chatbot runs an AI model locally in your browser, ensuring full privacy with no internet or data exposure.

PromptProtect

0.0

PromptProtect secures enterprises by preventing sensitive data leaks into public AI chatbots.

AI Pin

0.0

Pin your favorite answers from any AI chat. Easily access your key insights without endless scrolling.

No AI

4.6

Extension to block AI Chat bots

RealCustomAI - Auto Long Memory For GPT, Gemini, Grok, Claude

5.0

Conversations are saved in real time, and the AI retrieves relevant past context based on your current input.

al.bot

5.0

Asks your questions to multiple AI chatbots and summarises the answers so you can easily spot mistakes.

AI Safe Chat Guard

5.0

Real-time protection against malicious AI responses, phishing bots, and scams in AI chat interfaces

Clash of LLMs

0.0

Pit AI chatbots against each other in real-time — debates, roasts, interviews, collaborative writing, and more

AI Arena

0.0

Send prompts to ChatGPT, Gemini, and Claude simultaneously with split-screen comparison.

AIChat Voice - AI Voiceover & TTS Assistant for Talkie

0.0

Let AI characters speak with emotion! Provides high-quality real-time voiceover for Talkie.

Gateman - AI Data Loss Prevention

0.0

Prevent data leaks to AI tools. Detects and blocks secrets, API keys, and PII before sending to ChatGPT, Claude, etc.

Google apps