News for hackers. Stuff that matters.
Re:AI behavior guardrails should be public by _heimdall on Wednesday February 21, 2024 @04:53PM (#39460115)
A good fix would, in my opinion, understanding how the algorithm is actually categorizing and why it miss-recognized gorillas and humans.

If the algorithm doesn't work well they have problems to solve.

Re:AI behavior guardrails should be public by CydeWeys on Wednesday February 21, 2024 @08:06PM (#39461820)
It's too costly to potentially make that mistake again. So the solution guarantees it will never happen again.
Re:AI behavior guardrails should be public by DeusExMachina on Thursday February 22, 2024 @04:09AM (#39464837)
But this is not an algorithm. It's a trained neural network which is practically a black box. The best they can do is train it on different data sets, but that's impractical.
Re:AI behavior guardrails should be public by _heimdall on Thursday February 22, 2024 @08:34AM (#39466797)
That's exactly the problem I was trying to reference. The algorithms and data models are black boxes - we don't know wat they learned or why they learned it. That setup can't be intentionally fixed, and more importantly we wouldn't know if it was fixed because we can only validate input/output pairs.