Three AI safety errors that can hang-out enterprises

We dwell in a world the place anybody can publish to npm or PyPI, and we’ve seen attackers slip malicious packages into these ecosystems or compromise ones which might be broadly used. A few of the current incidents have concerned safety and devops instruments themselves pulling a compromised dependency, operating it as a part of CI/CD with elevated privileges, and quietly exfiltrating secrets and techniques or tampering with builds. I personally skilled any such compromise a few months in the past, and needed to replace all of my credentials in GitHub.

Pulling unvetted code is unhealthy; now layer AI brokers on high of that. They default to no matter is best to find and combine. If a bundle solves an issue in entrance of the agent, the agent will add it. That is the previous “obtain a random library from the Web” downside, however now it’s on autopilot, at scale, and shifting at a tempo we’ve by no means seen earlier than.

To resolve this downside, we should present the brokers with an innate sense of our danger tolerance, an authorized parts listing, our needs round logging, and so forth. We are able to do that with spec information and what the trade calls constitutions. Collectively, that is known as harness engineering, which we’ll speak extra about later.

Related Articles

LEAVE A REPLY

Please enter your comment!
Please enter your name here

Latest Articles