LLMs are still surprisingly bad at some simple tasks
SMRTR summary
When asked to identify TLDs that match HTML5 element names, three major LLMs (ChatGPT, Gemini, and Claude) failed at this simple comparison task. ChatGPT missed several matches and listed a nonexistent TLD, Gemini completely misunderstood the question, while Claude identified seven correct matches but missed many others. This demonstrates that despite their capabilities, LLMs struggle with basic tasks that even teenagers could perform, appearing convincing only to those unfamiliar with the domain.
SMRTR provides this summary for quick context. The original article belongs to Hacker News.
Read the original article