Hacker News Reader

Comment by ricksharp | Hacker News Reader

This might work today, but it won’t work tomorrow.

This is just one side of a GAN, on the next iteration, it will be defeated.

Bottom line is that if a human can recognize, then it is possible for a machine as well.

Also, given that the big networks can just keep throwing more resources at it (I.e. GPT-3), it’s just a matter of increasing the network size to improve feature redundancy.

View on HN

More accurately, if a human can accurately label inputs and measure outputs, it's possible for a machine. The human eye isn't the peak, just our current standard.

its not the eye thats doing the recognition. The human brain is still more impressive than any machine

I agree that it won't work tomorrow. To have a system that would continually work you would need to get access to an API that performs facial recognition and then continuously have the system perform queries on that system that would monitor that the facial recognition would fail.

Actually the system breaking tomorrow isn't likely to be the case due to the transferability property of adversarial examples.

Adversarial examples transfer between different models trained on different datasets with different architectures.

A new model from yesterday's data is essentially the same architecture, just with some fluctuations in decision boundaries.

Might it affect the success over time? Sure. But not tomorrow.

Reply on news.ycombinator.com