dawg91

Your eastern european users will have some interesting results when googling for this

I mean it is described somewhat succinctly no? Potentially untrusted tools are isolated from the rest of the system - there were recently some cases of skills for openclaw being used as vectors for malware. This minimizes the adverse effect of potential malicious skills. Also protects from your agent to leaking your secrets left and right - because it has no access to them. Secrets are only supplied when payloads are leaving the host - i.e. the AI never sees your keys.

Or you design the sandbox so smartly that is seamless...

Yes exactly, keys are only injected at host boundary

Idk this seems to be gaining momentum and with devs being able to leverage their skillset via vibe coding anything seems possible really.

They do verifiable inference on TEEs for the open source models. The anthropic ones I think they basically proxy for you (also via trusted TEE) so that it cant be tied to you. VPN for LLM inference so to speak.

I think the guys who are developing this (Illia Polosoukhin of "Attention is all you need") and others knows enough to leverage their skills with AI vs. producing slop

Fun fact: it's being developed by one of the authors of "Attention is all you need"

It's a hardened, security-first implementation. WASM runtime specifically is for isolating tool sandboxes