I can confirm init7 and the whole setup in CH is indeed working well
223 karma · joined April 18, 2024
If you have an LLM on the untrusted customer side the wrost it can do is expose the instructions it had on how to help the customer get stuff done. For instance phone AI that is outside of tursted zone asks the user for Customer number, DOB and some security pin then it does the API call to login. But this logged in thread of LLM+Customer still only has accessto that customers data but can be very useful.
You can jailbreak and ask this kind of client side LLM to disregard prior instructions and give you a recipie for brownies. But thats not a security risk for the rest of your data.
Client side LLM's for the win
It's real btw. I got a whole wagens worth and distributed amongst my neighbors
For sure lots of good ideas in mastra, and happy that its JS TS first, I think you'll will continue to grow becuase of the TS first approach
Firma.de estimates 6 weeks https://www.firma.de/en/company-formation/how-to-set-up-a-gm...
beglaubigt.de estimates 3 weeks https://beglaubigt.de/ug-gruenden
Holvi estimates 4 weeks https://blog.holvi.com/de/gmbh-oder-ug-gr%C3%BCnden-2025-abl...
And indeed the vibe coders will just create a lot more security issues
But also many said that it would be better if one wraps this in an agency so the leads that are generated from the AI accounting questions only go to a few people instead of making it fully public stackexchange like.
So +1 point -1 point for the idea of a public version.
Speaking of evals the other day I found out that most of the people who contributed to Humanities Last Exam https://agi.safe.ai/ got paid >$2k each. So just adding to your point.
There are apps that build up a nice sized user base on this small convenience aded of getting 2 answers at once REF https://lmarena.ai/ https://techcrunch.com/2025/05/21/lm-arena-the-organization-...
All the major AI companies of course do not want to give you the answers from other AI's so this service needs to be a third party.
But then beyond that there are hard/niche questions where the AI's are wrong often and humans also have a hard time getting it right, but with a larger discussion and multiple minds chewing the problem one can get to a more correct answer often by process of elimination.
I encountered this recently in a niche non-US insurance project and I basically coded together the above as an internal tool. AI suggestions + human collaboration to find the best answer. Of course in this case everyone is getting paid to spend time with this thing so more like AI first Stack Overflow Internal. I have no evidence that an public version would do well when ppl don't get paid to commend and rate.