Together.ai: Prompt Leakage for Requests

Fe2O3 13 points 6 comments November 22, 2026
www.together.ai · View on Hacker News

Discussion Highlights (4 comments)

nickandbro

The mass hacking continues…

sans_souse

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?

tczMUFlmoNk

> 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.

alwa

…I was wondering why Claude started recommending a layer of high-perplexity canary tokens for a document-watermarking project I was working on…

Semantic search powered by Rivestack pgvector
13,334 stories · 126,150 chunks indexed