Google AI Overview spelling errors go viral as users expose persistent flaws in search overhaul

Google's AI Overview still can't spell, and the internet is very aware of it

Google's AI tools remain abysmal at answering questions about spelling, having gone viral two years ago for responding to the question "how many r's are in the word strawberry?" incorrectly. But it's still bad. On Tuesday, X user Naomi Rohatyn tested the large language model's (LLM) current ability to answer to a spelling question. "How many e's in the word astronomical?" they asked. "There are exactly 2 'e's in the word "astronomical" (a-s-t-r-e-n-o-m-i-c-a-e-l)," replied AI Overview. This Tweet is currently unavailable. It might be loading or has been removed. We tried it ourselves, getting the same answer. It appears to work for any word with four or more syllables: Suffice to say, people are having another gleeful round of testing the technology's spelling weakness, sharing their findings on social media. This Tweet is currently unavailable. It might be loading or has been removed. This Tweet is currently unavailable. It might be loading or has been removed. This Tweet is currently unavailable. It might be loading or has been removed. I don't want to be all Billy Madison spelling bee about this, but considering users are less likely to click on links when an AI summary appears in the results, surely the information provided in AI Overviews should be accurate. But it's complicated. AI chatbots need exact context and specifics to answer as well as they can, so surely spelling words within their training data seems easy. However, things get knotty when you ask an LLM to consider words letter-by-letter, as the model will process text in chunks rather than individual characters (it's called tokenisation). I thought I'd ask Google's Gemini itself, to see what it had to say for itself. Defend your poor spelling! "The short answer is that I don't look at or write text the way you do," Gemini told me. "When you write the word 'apple,' your brain processes five distinct letters. When I read or write text, I see the word as a single unit called a token (a numerical representation of a word or part of a word). "Because I process words as whole blocks of meaning rather than strings of individual letters, I don't naturally 'spell' out words sequentially. I know exactly what 'apple' means and how it relates to other words, but I don't inherently focus on the fact that it contains two 'p's unless specifically asked to break it down." Mashable has reached out to Google for human comment.

Google's search overhaul has social media users baiting the 'AI Overview' to prove a point

It's been just over a week since Google announced a controversial overhaul of its search engine. Rather than answering queries with a list of links, Google Search's AI Mode now drops users into an interactive AI-powered search box, an expansion to the AI overview features that have been part of Google Search since 2024. From there, users are able to ask follow-up questions within that AI search box, negating the need to access any websites beyond Google Search itself. The news broke the internet as social media lamented that Google was, well, breaking the internet. Users pointed out that Google's AI overviews are still rife with errors, and argued that expanding the search engine's AI integration might only exacerbate those problems. To prove their point, social media is subjecting Google's AI to an internet-wide spelling bee -- one that it's failing spectacularly. For some reason, Google's AI can't seem to keep track of even basic spelling. Take one viral post where a user asked Google how many letter Ls are in the word "google." The AI replied that there are two Ls, then respelled (and misspelled) the word to show where: "Goolle."