they aren't going to follow rules reliably, they need to be trained with these recognize ambiguity and ask patterns
unfortunately, the labs have different goals that are not aligned with uses who want this
current training is try anything any everything to get the task done, human free operations... it sells more tokens, they have massive investments and debt to return on
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
Hmmm so basically why AI agents get to learn about me but I dont have one set of rules that follows me across all of them
Well I got a chance to look at the website seems interesting enough a mailbox to manage your personal agents with rules? https://trinitite.ai/
they aren't going to follow rules reliably, they need to be trained with these recognize ambiguity and ask patterns
unfortunately, the labs have different goals that are not aligned with uses who want this
current training is try anything any everything to get the task done, human free operations... it sells more tokens, they have massive investments and debt to return on
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
Battery usage, people don't want their phone to go into coma so quickly
I'm not even sure what I need an LLM to do with/on my phone, what are people using these things for?
Also, I have zero trust for Jev like models and use rerankers/policy-tuned llms for some of what you are concerned with