News for hackers. Stuff that matters.

A comment on Risk Assessment of GitHub Copilot. Parent comment

Re:Risk Assessment of GitHub Copilot by jtbayly on Monday July 12, 2021 @04:15PM (#27814542)
I would have thought to pivot to an assistive model in the case you mention, and in cars and in copilot.

Have the machine notify you when it thinks you’ve made a mistake.

[ Parent | on HN ]
Re:Risk Assessment of GitHub Copilot by mumblemumble on Monday July 12, 2021 @04:31PM (#27814722)
The thing we ran into was, in cases where the human and the machine disagreed, it was basically never the human that was wrong.
[ Parent | on HN ]