Comment by no_no_no_yes
1 day ago
> I've also been working on an open source protocol / reference implementation for user-owned AI memory
I've thought about how to fix this too. I'm "locked in" to OpenAI because of what it knows about me. Literally it's told me things like "blah blah but you shouldn't do that because you take X medication which has Y in it" and I'm like "...really? can you reference that?" and it gives me some old thread where I chatted about it and unbeknownst to me I completely forgot.
In other words it's legit helpful as my "second brain", but I also don't like that I'm locked in and can't bring all this shared memory/context over.
Yes, exactly. Over the past few months I've been trying to refine the vision here - it started with me thinking about my own use case in personal AI, and now has grown into me understanding how there's actually an pervasive governance problem in agentic applied AI right now - we know inference is inherently fallible and yet have none of the open standards for trust and safety we know can protect consumers and businesses.