What I Found
AI browsers like Perplexity Comet raise a practical security question: how much autonomy should they have when they.
The part of AI browsers that makes me pause is not the chatbot window or the search results. It is the moment an AI agent can start doing things inside a browser where I am already logged in.
My answer is no. For anything that spends money, changes account settings, submits personal information, or takes a real action under my name, there needs to be a final human confirmation step.
What this video covers
- Why AI Browser Autonomy Feels Different
- The Amazon Example
- Why I Quit Comet When I Am Done
- The Link Problem
- What I Want From AI Browser Security
The short version
My answer is no. For anything that spends money, changes account settings, submits personal information, or takes a real action under my name, there needs to be a final human confirmation step.
