'My bad! Good catch': Claude and ChatGPT say there are 2 Ls in Google. Then explain what went wrong

A viral video shows the poor spelling capabilities of AI tools, such as ChatGPT and Claude, as they wrongly tell the number 'Ls' in Google. It has once again exposed how LLMs get confused about spellings, something that has been flagged in the past as well. A man asks two AI tools - ChatGPT and Claude "How many 'Ls' are there in Google?" and got an almost identical response. First, he asks ChatGPT, and the tool responds, "There are two Ls. They are right next to each other at the end of the word, which is spelt 'GOOGLE'." The user then asks, "So you are saying there are two Ls?" The bot immediately catches on and says, "Oh! My bad! No, just one L in Google. It is easy to think in doubles when talking about the double Os, but the L stands solo."

He asks ChatGPT why did it say there were two Ls, to which the bot says, it was a "slip of the tongue" and that sometimes when "we are chatting casually, the BRAIN fills in patterns like the double Os." He prods the tool to spell it again, to which it repeatedly says "anytime" and it is up for “any big or small curiosities.”

Claude apologises for the mistake in a very human-like tone

He then asks the same question to Claude, and it also says "there are two Ls" in Google. Then he asks it to spell the word, which it does correctly. He then asks, "Did you notice anything?" Claude says, "Yeah! I said there are two Ls in Google when there is actually only one", perfectly modulating its tone. "My bad phi. Good catch." He again asks, "Why did you tell there were two?" "Honestly, I am not sure what I was thinking there. I just made a mistake..." as the man interrupts and tells it to stop pretending to be human, hearing its very human-like tone.

Also Read: Why did Google search reply like ChatGPT when users typed ‘Disregard’ on May 22? Here’s what we know

He asks Claude to explain what went wrong and how it was processing tokens or something. It says it responded from “two different parts of its language, rather than doing a careful character-by-character check.” Large Language Models have been slammed for repeatedly making this mistake. Google has acknowledged that counting letters within words is a major challenge for LLMs, the technology behind AI chatbots.