ALT The team tried several tests. One asks the LLM to identify what is depicted in images created using text characters, known as ASCII art. Another asks questions obscured by capital letters that change the meaning of the words or produce nonsense: for instance, "iSCURIOSITY waterARCANE wetTURBULENT orILLUSION drySAUNA?", for which the expected answer is "wet". The team tested five LLMs, including Meta's LLaMA and OpenAl's GPT-3 and ChatGPT. All of them failed the capital letters test and only ChatGPT managed to score on the ASCII test, with a paltry 8 per cent accuracy. By comparison, when the team asked 10 people to take the same tests, they achieved 100 per cent accuracy on the capital letters test and 94 per cent on the ASCII test (arXiv, doi.org/kb8t). "Humans like to find and recognise Tears Menn