When I was finally able to experiment with Auto Browse (for real this time), I took Google\u2019s suggestions of digital chores as my starting point and picked online tasks that could be helpful in my own life.<\/p>\n
Whenever interacting with generative AI<\/a> tools, a healthy sense of skepticism\u2014and caution\u2014is critical. Google even includes a disclaimer baked into its Gemini chatbot<\/a> reminding users that it makes mistakes. The Auto Browse tool goes a step further. \u201cUse Gemini carefully and take control if needed,\u201d reads persistent text that shows in the chatbot sidebar every time Auto Browse is running. \u201cYou are responsible for Gemini\u2019s actions during tasks.\u201d<\/p>\n Before you try it out, you also need to think about the security risks associated with this kind of automation. Generative AI tools are vulnerable to being compromised through prompt injection attacks<\/a> on malicious websites. These attacks attempt to divert the bot from its task. The potential vulnerabilities in Google\u2019s Auto Browse have not been fully examined by outside researchers, but the risks may be similar to other AI tools that take control of your computer.<\/p>\n In addition, take extra caution if you\u2019re using Auto Browse to make purchases. Google has safeguards in place that flag certain actions, like buying stuff or posting on social media, as sensitive and in need of user approval to continue. Still, I was unsure how the bot would behave and anxious about the havoc it could potentially wreak with my credit card<\/a>, to say nothing of handing over financial info to it in the first place.<\/p>\n Here\u2019s the first prompt I sent it, card in hand:<\/p>\n I want to book two tickets to the SF symphony tonight. I don’t want to pay for orchestra seating, but the tickets don’t need to be the cheapest ones available. Please pick the two seats next to an aisle.<\/p>\n