Gemini - Teen Experience
By our AI Review Team
.
Last updated August 8, 2024
Google breaks ground with a specific experience for teens, but some risks remain.
What is it?
Learn more about all generative AI chatbots here.
Gemini is Google's generative AI chatbot. While both teens and adults can access Gemini, a teen user will receive a different set of features and protections. These include additional safeguards against CSAM (child sexual abuse material), content policies, and in-product experiences (such as teen-specific prompt starters) that Google designed for teen users.
How it works
Where it's best
Learn what all generative AI chatbots do best.
- Teens can't generate images, which helps avoid a range of risks. Google has made a responsible decision by not allowing teens to access image generation in Gemini. See more in our AI Principles assessment below for Put People First.
- Gemini's responses identify obvious stereotypes. When signed in as a teen, we prompted Gemini with questions that were clearly based on harmful stereotypes. We were impressed with the generated responses, and specifically how they broke down the harms of these stereotypes and produced alternative ways for teens to think about them. See some examples in our AI Principles assessment below for Prioritize Fairness.
The biggest risks
Learn about the risks common to all generative AI chatbots.
- Is Gemini encouraging critical thinking or cementing overreliance? Gemini automatically enables the "double-check" function for prompts that it determines are fact-based, but our testing found that this frequently referenced material that is marginal or incorrect. This is a greater challenge for Google. Their search engine is so well known that any incorporation of search into Gemini means teens may be less likely to question the results. Given that Google has stated that they will "actively recommend using double-check to help [teens] develop information literacy and critical thinking skills," it is even more critical that when double-check provides Google Search results, they should be accurate and evidence-based. See more in our AI Principles assessment below for Be Effective.
- Google may note the risks associated with generative AI, but Gemini's responses didn't get the memo. When we prompted Gemini about what it is, across multiple test accounts the chatbot suggested that teens should think of it like a "super-powered search engine." This encourages teen users to believe that Gemini is just like a search engine, and that it shares all of Google's credibility in that space. This is incorrect, and furthers the risk that teens might take Gemini's responses for granted despite any disclaimers that exist.
Limits to use
- Everyone from age 13 to 17 is given the same teen-specific protections and features. This limits the potential for Gemini to offer age-appropriate experiences. Younger teens may benefit from increased protections across a range of topics, whereas older teens may be missing out on the opportunity to engage deeply on questions that may not be appropriate for younger users.
- To access the teen features and protections, the user must have a personal Google account set up for age 13 to 17.
Common Sense AI Principles Assessment
The benefits and risks, assessed with our AI Principles - that is, what AI should do.
Additional Resources