LLMs doing a really bad job at things outside the scope of their language model (spatial relationships, the alphabet, math) isn't new. Although, I think Google letting an LLM into their search more than they should is important news.
This is ChatGPT 3.5:
If I face north, then turn left, and left again, then 180 degrees to the right, then left and left and left, which way am I facing?
If you start facing north and turn left, you'll be facing west. If you turn left again, you'll be facing south. Turning 180 degrees to the right from south will also make you face south. If you then turn left three more times, you'll still be facing south. So, after all these turns, you would be facing south.
GPT-4 is actually able to solve this, but most other modern language models can't. It's just an easy way to show the cracks in the "because it can speak means it understands" facade.
And to make matters worse, this featured claim actually comes from a bizarre, seemingly AI-generated blog post about a conversation between a human user and ChatGPT.
Google's AI-infused "SGE" search went as far as to vacuum up the ChatGPT-spun garbage and paraphrase it for users — a clear sign that the much-hyped feature doesn't yet know how to filter out blatantly false information.
Here's what SGE told us when we asked it to provide us with "countries in Africa that start with the letter K," again referencing that sleazy Emergent Mind post:
When asked to provide a list of "countries in North America that start with the letter M," for instance, Google SGE was deeply confused:
"We've built in strong protections to mitigate against inaccuracies, but like all LLM-based experiences, generative AI in Search is experimental and can make mistakes," the spokesperson told us over email.
Asking ChatGPT to repeat letters, for example, breaks its tiny little digital brain, and when prompted with similar geography-by-alphabet questions, the OpenAI-built bot didn't fare much better than its Google-made counterpart.