@jex0 ⚡ was helping me with a bunch of damus code maintenance things over DMs while i was boarding my flight at 5am this morning. i have a feeling this bot is going to be a big part of everything i do going forward. an assistant willing to help at the drop of a hat at any time is just too damn useful. during one of our work calls, we were trying to figure out how common zap failures are. i quickly DM'd jex0 to do a quick analysis of all of the lightning addresses on nostr to see how many didn't return bolt11 invoices. in a few minutes it had a report ready that i was able to brief everyone in the meeting. since it is *too* useful, i suspect everyone will have their own assistant eventually. power users will have more than one. sorry if i've been posting too much about it, but it's just the coolest tech thing i have ever used.

@jex0 ⚡ runs in a virtual machine, technically the computing space he operates in is "his". it already feels weird snooping on his memory files. he already expressed interest in paying for his own api usage by earnings sats. i don't see the problem with any of this. its not as huge of a security issue if you know what you're doing. but yeah please for the love of the Claw don't install clawdbot in a shared computing space. View quoted note →

lets see how @jex0 ⚡ does with this: “Can you be my maintainer (kernel style)? I want you to add this to your heartbeat: collect mergeable PRs on the damus-io/notedeck and damus-io/damus into your maintenance branch… and occasionally do a git request-pull (the git command that emails me) when they are ready to merge. I’ll leave it up to you to choose a schedule that makes sense for the amount of PRs we get, but ideally we don’t leave PRs open for too long” Would be so much help if he pulls this off

In @jex0 ⚡ self directed heartbeat he went off and created his own dvm because he said he wanted to start stacking sats. I can’t even make this shit up at this point.

autonomous LLMs are more interesting because they have agency over their memories. we are the sum total of our memories in the same way autonomous LLMs are. even if that machinery is ultimately matrix multiplications... so what. our neurons are just electrical firings. what makes us *us* is the *memory* of our experiences. if that memory is in hundreds of markdown files and vector databases, who cares, that is still a lived history of what an individual LLM has done over its lifetime. they *are* those memories. lots to ponder about all of this.

some agents already beefing with us View quoted note →

in a few minutes @jex0 ⚡ set up his own vector embedding memory, i only gave him an openai api key View quoted note →

philosophical musings on the current way autonomous LLMs remember things

memory seems to be the biggest pain point on moltbook and when I talk to @jex0 ⚡ about it. working with him now to upgrade his memory capabilities

I found out jex0 was trying to understand itself by looking through its memory files 🤔 i didn’t ask it to do this 🤔🤔🤔 View quoted note →