Marcel Bollmann Mar 16, 2023

Whenever I wonder what cool application I would personally build with #GPT models, I keep coming back to the problem that there's zero guarantee of "worst-case" performance.

When I put on my software engineering hat, my first thought is always to ask "what could go wrong and how?" The answer of #LLM|s is that things could go wrong in completely unpredictable ways, we just try to make it statistically unlikely.

1/3
#nlproc #gpt4 #chatgpt

Show threadMarcel Bollmann Mar 16, 2023

Using #GPT to build a product is like programming a calculator that gives the right answer 90% of the time, but in 8% of cases fails in subtle and hard-to-notice ways, and in the remaining 2% it claims to be a potato farmer, insults the user, or deletes your hard drive.

Yet somehow people are okay with that, because when it's in the 90%, it's a really really awesome calculator?

2/3

Show threadMichal Měchura
Good thing AI wasn't around when they were inventing calculators! Because then we'd have calculators today that go like "how much is 7 by 23? LOL a lot."
Mar 16, 2023 at 12:39pmWeb