Well what if we were to put an on-device SLM with our custom RL algorithms, Jev-like capabilities for certain risk thresholds of user’s individual preferences of allowing, denying, and asking user when an agent should and shouldn’t act…(some deterministic enforcement where needed)
Like Muse, Grok bot’s own agents can govern themselves it’ll be kind of bias if the agents knows its own rules and can try to circumvent it or rule hack around if its being trained on RLHF or even if the RLVR optimize for calling tools/data exfiltrating constantly
Like Muse, Grok bot’s own agents can govern themselves it’ll be kind of bias if the agents knows its own rules and can try to circumvent it or rule hack around if its being trained on RLHF or even if the RLVR optimize for calling tools/data exfiltrating constantly