"Imagine a world where scientific experiments yielded different results every time you ran them, even with identical setups.

[dw_innovation@mastodon.social]

"Imagine a world where scientific experiments yielded different results every time you ran them, even with identical setups. (...) In most fields, such inconsistencies would be unacceptable. Yet, in the (.) world of large language models (LLMs), we’ve often accepted a curious paradox: the same prompt, run multiple times, can produce entirely different outputs."

Anthony Laneau for @hackernoon:

https://hackernoon.com/the-unseen-variable-why-your-llm-gives-different-answers-and-how-we-can-fix-it

#AI #LLM # nondeterminism