Hacker News Reader

Here are 2 examples from the Black Spatula project where we were able to detect major errors: - https://github.com/The-Black-Spatula-Project/black-spatula-p... - https://github.com/The-Black-Spatula-Project/black-spatula-p...

Some things to note : this didn't even require a complex multi-agent pipeline. A single shot prompting was able to detect these errors.

View on HN

This black spatula case was pretty famous and was all over the internet. Is it possible that the AI is merely detecting something that was already in its training data?

This is the original work that detected the problem.

I found many sources on the internet that state that the error in the black spatula paper was discovered by John Schwarcz of McGill University while reviewing a research paper:

[1] https://www.expatgo.com/my/2024/12/15/an-error-in-arithmetic... [2] https://gizmodo.com/embarrassing-math-error-scared-the-pants...

Is John Schwarcz behind this Yesnoerror or the black spatula project?

Reply on news.ycombinator.com