mens_rea

Deeply flawed paper for several reasons:

* Small data set of 2 runs (!!)

* Exaggerated claims (saying A1 beat 50% of testers, yet only 4/10 testers found LESS vulns than A1, and A1 had a nearly 50% false positive rate)

* AI agents were given 16 hours while human testers were given 10

* Their human testers gave up when a modern browser refused to open a webpage with weak TLS ciphers so....clearly not professional testers unless the bar is REALLY low these days

There were also more loaves of bread sold than window machines in 2012Q3.

Oh, sorry, I thought we were just comparing unrelated things to 'prove' Microsoft is in trouble...

I don't imagine he tossed in digitizer as a requirement just for the giggles.

Nope. No Digitizer. Thanks for playing.

I love that this title is so unbiased and doesn't at all blow the document out of proportion or make it appear more sinister than it actually is.

Thank you for not misleading readers with your title in order to get views and points.

Exactly the points I wanted to make. The article is vague at best and no statistical evidence is presented anywhere.