AI companies in race to demonstrate their model most threatening to humanity
Thread
Unofficial Hacker News client; not affiliated with Y Combinator.
AI companies in race to demonstrate their model most threatening to humanity
Unofficial Hacker News client; not affiliated with Y Combinator.
ACCount39 · · focus · HN ↗
OpenAI, for example, thought their sandboxes were good enough. As their AIs got more and more advanced, they kept proving them wrong - sandbox after sandbox.
And that's today's AI problems. AI capabilities are still improving - if there's a limit to that, we are yet to find it. Coupled with how willing today's AIs are to break the rules and resort to "hack the world" in their problem solving? Very concerning.
nicce · · focus · HN ↗
What I have been reading, was that their sandboxes were so poor that it was pure negligence. I am still waiting to see if some external and neutral cybersecurity company with high reputation would audit their sandboxes and how they are being used.
DennisP · · focus · HN ↗
That seems pretty locked-down to me. I don't think it's reasonable to expect companies to find all the unknown vulnerabilities in any third-party software they use.
<a href="https://securityaffairs.com/195774/ai/openai-ai-models-exploited-zero-days-to-reach-hugging-face-in-benchmark-test.html" rel="nofollow">https://securityaffairs.com/195774/ai/openai-ai-models-explo...
nicce · · focus · HN ↗
It is reasonable to expect for companies to select third-party components that are fit for the purpose. Artifactory was not running in the sandbox, but rather as the edge, so it is in the sandbox'es trust boundary. Same sandboxing requirements would apply for this software too as it is pure dependency.
Security trust boundary was extended to include Artifactory as a dependency, but Artifactory was not fit for the job, and sandboxing failed. And as the network isolation was not good enough, the impact was catastrophic.