ChatGPT, OpenAI's artificial intelligence chatbot, is flexing its muscles on social media over how “at long last” it can correctly tell how many “r's” a “strawberry” contains. The answer is obvious, ...

ChatGPT passes “strawberry” test but fails when switched to “cranberry” AI still struggles with simple letter-counting despite broader improvements Reasoning tests like “car wash” still expose gaps in ...

Confident mistakes – or lies, if you will – are a common problem of large language models used in AI chatbots, with one common shortcoming of ChatGPT being that it would frequently miscount the number ...