deliberate pigheadness is not intelligence

Show hard words

three hypothetical Ai queries:

  • how often do "disaster tribes" produce the winner on Survivor
  • how often do people born in February get voted out before the merge on Survivor
  • how often do people who use an idol win Survivor

questions only of interest to a certain type of compulsive fan ... or a person who noticed something and is curious

----

how do we solve this?

We do NOT just train an LLM on all the survivor results and hope it can think it out. No. We use a database. The LLM can build the database. The LLM can make the database query. The LLM can design the system to do steps 1 and 2. What it can't do is give the result fully-formed, like Athena jumping out of the head of Zeus.