Data Processing Incidents on Inference Providers
sdko
76 points
29 comments
November 22, 2026
Related Discussions
Found 5 related stories in 170.2ms across 13,334 title embeddings via pgvector HNSW
- OpenAI discloses four more rogue incidents DASD · 123 pts · October 17, 2026 · 55% similar
- OpenAI discloses six new AI safety incidents toomuchtodo · 23 pts · September 17, 2026 · 54% similar
- OpenAI Discloses Six New Incidents of ‘Concerning’ A.I. Behavior jbegley · 66 pts · September 17, 2026 · 54% similar
- Hetzner Experiments Platform: Inference API sparkling · 15 pts · August 10, 2026 · 53% similar
- Cerebras Disaggregated Inference emschwartz · 59 pts · November 18, 2026 · 53% similar
Discussion Highlights (10 comments)
redrix
Nice to see this move by OR. That being said, the best ZDR agreement is the one that your company has directly with the inference provider(s). Unfortunately: - Not everyone is large enough (or has enough $$) for that. - Ultimately you’re in the same position of having to “trust” that they’re doing ZDR; even after auditing their security docs.
Havoc
Solid move. Though frankly I would think anyone even slightly bothered about ZDR does not start their train of thought with "OK so we're going to put a middle man in"
solarkraft
With this change, everything is good in the world and we can just take everyone’s word that they’re actually ZDR without any audits or technical enforcement again. Right?
the_lucifer
Is there any information on the three companies that violated ZDR? I could only find mention of one of those affected providers in the original article (that OR links in their post): Lark. Trying to figure out if I ended up routing to one of the affected "ZDR" endpoints. I don't understand why these names are being coyly tiptoed around as if they're trying to protect the privacy of these companies blatantly lying about ZDR. Why isn't OR calling out the actual providers they off-boarded by name? Why is OR basically protecting them under a cover of anonymity? Lost a lot of trust in OR that's for sure, in-spite of some other positive reception I see here for this move. Edit: Wording update.
mbgerring
You should assume that no inference provider is honoring any public commitment they have made about data retention. You should assume that 100% of what you share with an LLM over the wire is being recorded, saved, and used as training data. Any other stance is indefensible naïveté for anyone who has been around the tech industry for more than, let’s say, 5 years.
g-b-r
I hope this time this stays on the frontpage, every LLM user should be aware of it. There's also a good article at https://arstechnica.com/security/2026/11/a-leaky-ai-supply-c... , and a few earlier comments at https://news.ycombinator.com/item?id=50582794 , https://news.ycombinator.com/item?id=50585962 and https://news.ycombinator.com/item?id=50562582 .
cobychapple
Zero data retention, give or take 125 endpoints.
smuhakg
I got the email. The tl;dr is MiniMax (the Chinese AI lab) is actively reading your prompts, and a security researcher discovered this by putting decoy URLs into their requests which were accessed by MiniMax. More importantly, many providers (AtlasCloud, Novita and StreamLake were named but there seems to be more implied in the blog post) have been rerouting requests to MiniMax servers on the backend and not processing their own prompts. The obvious question is whether OpenRouter has done any auditing on their inference providers. Based on the researcher's blog post, I guess not. https://www.dragos.com/blog/ai-supply-chain-security-canary-...
g-b-r
This revealed something as delightful as a purported TEE provider having their "software TEE" root keys hacked, through "a legacy internet-facing service with management interfaces that relied on loopback access for trust and did not independently authenticate callers" ( https://phala.com/posts/phala-november-preliminary-incident-... )
a012
I was affected with just one prompt by this incident, which is non issue to me because I was trying different models at that time so there was nothing serious. The troubling problem I see in this incident is the “providers” in OR just casually forwarding prompts to upstream (MiniMax) instead of providing inference service them selves. Coincidentally later on I set my OR settings to only allow some providers that I can rely on, not blindly let OR route to wherever they like.