What are the barriers to external memory stores (assuming similar implementations), used via tool calling or MCP? Are the providers RL’ing their way into making their memory implementations better, cementing their usage, similar to what I understand is done wrt tool calling? (“training in” specific tool impls)
I am coming from a data privacy perspective; while I know the LLM is getting it anyway, during inference, I’d prefer to not just spell it out for them. “Interests: MacOS, bondage, discipline, Baseball”
I made a MCP tool for fun this spring that has memory storage in a SQLite db. At the time at least, Claude basically refused to use the memory proactively, even with prompts trying hard to push it in that direction. Having to always explicitly tell it to check its memories or remember X and Y from the conversation killed the usefulness for me.
I am coming from a data privacy perspective; while I know the LLM is getting it anyway, during inference, I’d prefer to not just spell it out for them. “Interests: MacOS, bondage, discipline, Baseball”