I will fly to India on Monday for a brief trip, and so I just spent an hour struggling through a very buggy online visa application process. Once I’d finished, since I now know what’s involved, I asked ChatGPT 4o about it. Most of these points are partially or completely wrong. This is an ‘unfair’ test. It’s a good example of a ‘bad’ way to use an LLM. These are not databases. They do not produce precise factual answers to questions, and they are probabilistic systems, not deterministic. LLMs to...