Chapter 5 of 10All chapters
Chapter 5 of 10
What to expect it to get wrong
Predictable failure modes.
Fabrication
Citations, statistics, quotations, dates and names are the highest risk, because plausible-looking versions are exactly what the process produces well.
- Confidence carries no information about accuracy.
- Asking the same question twice can yield two different confident answers.
Other weaknesses
Counting, arithmetic it cannot see through, very long documents, and reasoning about the physical world. Tools that let a model calculate or search cover some of this.