56 points sdko 2 hours ago 19 comments

redrix 2 hours ago | parent

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.

rkagerer 2 hours ago | parent

I'd say that's the second-best one. The most robust ZDR policy is running your own AI locally and enforcing the retention policy yourself.

az226 1 hour ago | parent

This right here.

ZDR is a marketing ploy. It’s not real. Only naive people believe it’s real.

msdz 27 minutes ago | parent

> Ultimately you’re in the same position of having to “trust” that they’re doing ZDR

Could it be a moat to offer a zero-trust (based on technical impossibility) ZDR solution for corporate customers, or is everyone who’s paranoid enough about that just going to host local models on-prem eventually?

edoceo 20 minutes ago | parent

Not an expert, I consult with medium size firms that so far have seen nice things from the AI. However, the lightly-informed C-Suite hears about the hacks and the data threats on CNBC/Bloomberg which has made them cautious. Even with their cursory understanding they are saying "can we look at these open models". N=2

wmf 8 minutes ago | parent

Multiple companies are already advertising TEE-based private inference.

Havoc 2 hours ago | parent

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 1 hour ago | parent

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 1 hour ago | parent

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 their "ZDR" endpoints.

I don't understand why these names are being coyly tiptoed around especially given the impact to workflows. Why isn't OR calling out the actual providers they off-boarded by name?

fedpost 1 hour ago | parent

Given how trust based the LLM world has to be right now, there should be zero tolerance for anyone doing stupid shit like this

SwellJoe 1 hour ago | parent

They state they notified customers who used any of the problem models via email (I got an email about it), which answers your question of whether you ended up routing to one of those endpoints. They apparently know who was routed to all those providers, so you don't have to guess.

That still leaves the desire of people to make informed decisions about what providers to use unresolved. If reputation is the only thing we have to go on when choosing a provider to send a bunch of sensitive data to, it'd be nice if the folks who actually know whether a provider is trustworthy would share that info.

But, since the email they sent identified the provider and the model (MiniMax, in my case) and the dates of use, it seems like it won't be secret for long what the other problem providers are. I'll assume the email to users of other providers will also include those details, so people can post about it even if OpenRouter is cagey about it in their blog post.

leafingensemble 52 minutes ago | parent

They just don't care. That is the reason.

mbgerring 1 hour ago | parent

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.

LeBit 26 minutes ago | parent

That’s why I never use a real email or real name.

The payment is where you have to provide real infos.

I just hope the payment infos is stored at a different place than prompt/conversations storage so mapping of user id to payment id is not trivial.

g-b-r 55 minutes ago | parent

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 42 minutes ago | parent

Zero data retention, give or take 125 endpoints.

smuhakg 40 minutes ago | parent

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 30 minutes ago | parent

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 28 minutes ago | parent

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.