logoalt Hacker News

Together.ai: Prompt Leakage for Requests

34 points • by Fe2O3 • today at 3:07 AM • 8 comments • view on HN

Comments

tczMUFlmoNk • today at 4:41 AM

> During development of our public GitHub repository, xorl, an AI coding agent committed a credential that provided access to the private Hugging Face repository

My emphasis on the accountability laundering. No, "xorl" did not do this—you did. And, if "xorl" is https://github.com/togethercomputer/xorl and `togethercomputer` is together.ai, then you wrote "xorl" and are doubly responsible.

If five years ago I had said, "During development of our public GitHub repository, my computer decided to commit a credential", this would have been immediately recognized for the embarrassing abdication of duty that it is. So, too, should this be now.

➕ show 2 replies
sans_souse • today at 4:35 AM

Am I inferring correctly here, in that Dragos basically had some sort of experiment set up and running for exactly this scenario, that effectively allowed them to trace the breach to the individual?

➕ show 1 reply
ChrisArchitect • today at 7:52 AM

Related:

Data Processing Incidents on Inference Providers

https://news.ycombinator.com/item?id=50595554

nickandbro • today at 4:31 AM

The mass hacking continues…