News for hackers. Stuff that matters.

A comment on I Lost Faith in Kagi. Parent comment

Re:I Lost Faith in Kagi by freediver on Friday April 12, 2024 @06:03PM (#40018149)
Yes, significant part of our effort is to build technology that detects LLM spam. We have a working model that detects LLM generated text with 90% accuracy currently. The plan is to integrate in search results and make available as an API.
[ Parent | on HN ]
Re:I Lost Faith in Kagi by oktoberpaard on Saturday April 13, 2024 @08:39AM (#40022777)
And just out of interest: what is the rate for false positives? An accuracy of 90% sounds very decent, as long as it doesn’t also filter out 10% of legitimate content.
[ Parent | on HN ]
Re:I Lost Faith in Kagi by lupire on Saturday April 13, 2024 @09:22AM (#40022976)
10% of infinity is infinity.

That's as good as 0% accuracy.

And AI text will keep changing.

[ Parent | on HN ]