I think this single fact is a major source of enshittification in large software products, especially in the era of ML/AI. If your quality is 99%, it sounds like "you have solved your task", but in reality there is a long tail that over time affects nearly every customer.
I've seen this so many times. 99% of search results are good (so within 100 queries you'll hit at least one bad result with p≈0.63), 99% of dashboard panes load normally (so a dashboard with 20 panes is broken in nearly 1 in 5 loads), and so on. If your LLM gets 99% of tool calls right, nearly every session will contain a malformed tool call.
Probabilities are hard for humans, probably.
I've seen this so many times. 99% of search results are good (so within 100 queries you'll hit at least one bad result with p≈0.63), 99% of dashboard panes load normally (so a dashboard with 20 panes is broken in nearly 1 in 5 loads), and so on. If your LLM gets 99% of tool calls right, nearly every session will contain a malformed tool call.
Probabilities are hard for humans, probably.