> Interesting that AI has doubled the number of CVEs detected in human written code in the past year, but when an AI causes a problem itself, people cry bloody murder.

The difference is that a human makes maybe a couple of mistakes a month (that actually make it into released code). What was that incident recently where Claude was filing PRs at the rate of a couple every second, creating serious security problems!?

When a human makes a mistake, it's fairly easy to clean up. When an AI makes a mistake it's a nightmare to clean up, it's everywhere!

> There is far too much seeing the glass a quarter empty, rather than seeing it three quarters full.

The trouble with Agentic AI, it's three-quarters full of the brown stuff you need a paddle to deal with.

> And I'm greatly looking forward to seeing just how hot the progress of open source software can get.

If we use AI as a servant, I would agree with you. But there are too many people bowing down to AI as their master. Therein lies disaster ...

Cheers,
Wol