Google says its AI will jetwash all traces of malodorous spam from your box

Google has proclaimed its rightful place among the Gods by creating an artificial intelligence so sophisticated it can block 99.9 per cent of spam - and this with only a 0.05 per cent false positive rate.

The rise of the machines is here, and now mankind has loosed them upon its spam it can be only a matter of time before they begin to stress test all of communications for whatever they deem to be weak in semantic content.

In an official gmail blog, Google has ruthlessly assessed its spam filters as still being unworthy of its majestic love, and has sworn to continue to improve them.

"Since the beginning," begins Google, "machine learning has helped make the Gmail spam filter more awesome."

In its earlier days, Google's AI had worked to destroy false YouTube views and sockpuppet spam. Now it will extirpate the more standard email spam.

When users decide to inform Google that it has mislabeled communications as spam, they are told that they are "not only improving your Gmail experience right then and there, you're also training Gmail's filters to identify spam vs. wanted mail in the future."

Keeping schtum on whether their AI has a secondary advertising purpose, the Oompa-Loompas say they recognise that "not all inboxes are alike".

The spam filters are now assessing which users enjoy weekly email newsletters and which users loathe them.

Finally, the spam filter is better than ever at rooting out email impersonation — that nasty source of most phishing scams. Thanks to new machine learning signals, Gmail can now figure out whether a message actually came from its sender, and keep bogus email at bay.

So say the Googlers ... if it is indeed them. ®