I started up a new city in Cities Skylines 2. Trying to build a city mate up of little pit stops along the highway with no industrial zones at all. It’s been an interesting experiment so far! The game does track the jobs generated by retail and city services, so if you balance it just right you can have enough work to attract residents and use the highway connections to just barely generate enough sales for the commercial zones to stay profitable. And the city as a whole is getting closer and closer to a positive balance in the budget, so I might just pull this off…
For those of you who didn’t read the paper, the argument they’re making is similar to Godel’s Incompleteness Theorem: no matter how you build your LLM, there will be a significant number of prompts that make that LLM hallucinate. If the proof holds up then hallucinations aren’t a limitation of the training data or the structure of your particular model, they’re a limitation of the very concept of an LLM. That doesn’t make LLMs useless, but it does mean you shouldn’t ever use one as a source of truth.