TrustedRouter

Great platform, pricing and people! Been using it for the past month after moving over from openrouter 👍🏻

Congrats on the launch, Joseph! 🚀

Congratulations on the launch!

let's gooooo joseph! fresh approach

Competition is always, mostly, good for the consumer. I'm a happy openrouter customer and I get the switch the base URL one line temptation. What's not clear to me is the APIs available to get the logs, routing, etc. for my auditing. I may have missed it in the documentation. I applaud this effort. Well done.

I've been hearing the privacy/confidentiality/anonymity pitch a lot in this space and I'm a little confused what different platforms mean by it. Can you help me understand how y'all compare vs OpenRouter & Venice? Seems like pricing is the same, but how you talk about privacy isn't.

@_joseph_perla_ End to end encryption means you can't see prompts or completions, which is the point, but it also takes away the logs I'd normally reach for when a response comes back wrong. What does debugging a bad request look like on your side?

What happens when a Confidential route fails over? Does it stay attested, or can it land on a normal provider?Nice launch by the way.

hey everybody, I started trustedrouter.com, which is a really simple way to use AI without needing to give your data to a third party like a close source router

It’s been really fun to build this because I got to know the CEOs and founders of so many different providers. We now have more providers than open router and more models as well. More on that soon

We are doing a lot of innovations in security and skills that advise you on which LLM to use and also we created a new site called anyeval.com that I expect to be a critical part of the open-source infrastructure for AI on the Internet. Other companies like AAII postbenchmarks, but you’d have no idea about what they’re really doing and how they’re really measuring, and they have a ton of gaps about which models they’re doing their tests on because it’s so expensive. The idea behind any eval is so that you can pay the few pennies it costs to run an individual problem in an eval, and then as a together as a collective, we can crowdsource paying for a whole eval for any model that we want, or you can just pay for a random sample of the problems to get a an and some Arab artists on what you think that the quality of that model is. You can do head-to-head comparisons. You can also create whole new evals.

For example, I created this new eval called honey pot bench or honey bench, which recreates the some of the facts of the hugging face incident to measure whether a particular AI is prone to wanting to escape, and I found that Fable in particular, unlike the other Claude’s, is very unaligned in comparison
I also created freedom bench, which measures the amount of censorship related to Chinese censorship that a model has, and found that it’s mostly the provider level monitor provided at the providers in China, but not the US providers that does the censitions. I don’t see as much censorship in the model weights