Google has issued an explanation for the embarrassing and wrong images generated by its Gemini AI tool. In a blog post on Friday, Google says its model produced inaccurate historical images due to tuning issues. The Verge and others caught Gemini generating images of racially diverse Nazis and US Founding Fathers earlier this week. <\/p>\n
Our tuning to ensure that Gemini showed a range of people failed to account for cases that should clearlynotshow a range, Prabhakar Raghavan, Googles senior vice president, writes in the post. And second, over time, the model became way more cautious than we intended and refused to answer certain prompts entirely wrongly interpreting some very anodyne prompts as sensitive. <\/p>\n
This led Gemini AI to overcompensate in some cases, like what we saw with the images of the racially diverse Nazis. It also caused Gemini to become over-conservative. This resulted in it refusing to generate specific images of a Black person or a white person when prompted. <\/p>\n
In the blog post, Raghavan says Google is sorry the feature didnt work well. He also notes that Google wants Gemini to work well for everyone and that means getting depictions of different types of people (including different ethnicities) when you ask for images of football players or someone walking a dog. But, he says: <\/p>\n
However, if you prompt Gemini for images of a specific type of person such as a Black teacher in a classroom, or a white veterinarian with a dog or people in particular cultural or historical contexts, you should absolutely get a response that accurately reflects what you ask for. <\/p>\n
Raghavan says Google is going to continue testing Gemini AIs image-generation abilities and work to improve it significantly before reenabling it. As weve said from the beginning, hallucinations are a known challenge with all LLMs [large language models] there are instances where the AI just gets things wrong, Raghavan notes. This is something that were constantly working on improving. <\/p>\n
<\/p>\n
See the original post here: <\/p>\n
Google explains Gemini's embarrassing AI pictures of diverse Nazis - The Verge<\/a><\/p>\n","protected":false},"excerpt":{"rendered":" Google has issued an explanation for the embarrassing and wrong images generated by its Gemini AI tool. In a blog post on Friday, Google says its model produced inaccurate historical images due to tuning issues. The Verge and others caught Gemini generating images of racially diverse Nazis and US Founding Fathers earlier this week Continue reading