A hackable AI assistant using a single SQLite table and a handful of cron jobs
21–30 of 183 posts
Re: A hackable AI assistant using a single SQLite table and a handful of cron jobs
#22Earlier quoted context omitted.
I’ve been thinking lately that email is a good interface for certain modes of AI assistant interaction, namely “research” tasks that are asynchronous and take a relatively long time. Email is universal, asynchronous, uses open standards, supports structured metadata, etc.
yep went down a rabbit hole trying to build a company around this. it’s the perfect UI text + attachments into the system, text + attachments out
My finance guy, tax attorney, other attorneys. Send emails, get emails, occasionally a blind status update from them.
Sure, we have phone calls, sometimes get together for lunch.
But mostly it’s just emails.
Re: A hackable AI assistant using a single SQLite table and a handful of cron jobs
#23Curious, how come you decided to use a cloud solution instead of hosting this on a home server? I’ve recently bought a mini PC for small projects like this and have been loving being able to host with no cost associated to it. Albeit it’s probably still incredibly cheap to use a IaaS or PaaS but still a barrier to entry for random projects I want to work on a weekend
I'd use a hosted platform for this kind of thing myself, because then there's less for me to have to worry about. I have dozens of little systems running in GitHub Actions right now just to save me from having to maintain a machine with a crontab.
Re: A hackable AI assistant using a single SQLite table and a handful of cron jobs
#24This is really cool. How much would that cost in Claude API calls ?
It's about 652 tokens according to https://tools.simonwillison.net/claude-token-counter - maybe double that once you add all of the context from the database table.
1200 input tokens and 200 output tokens for Claude 3.7 Sonnet costs 0.66 cents - that's around 2/3rd of a cent.
LLM APIs are so cheap these days.
Re: A hackable AI assistant using a single SQLite table and a handful of cron jobs
#25This made me think: what if my little utility assistant program that I have, similar to your Stevens, had access to a mailbox? I've got a little utility program that I can tell to get the weather or run common commands unique to my system. It's handy, and I can even cron it to run things regularly, if I'd like. If it had its own email box, I can send it information, it could use AI to parse that info, and possibly se…
- all attachments are stripped out and stored on a server in an hierarchical structure based on sender/recipient/subject line
- all discussions are archived based on similar criteria, and can be reviewed EDIT: and edited like to a wiki
Re: A hackable AI assistant using a single SQLite table and a handful of cron jobs
#26How? This post shows nothing of the sort.
"I’ve written before about how the endgame for AI-driven personal software isn’t more app silos, it’s small tools operating on a shared pool of context about our lives."
Yes, probably, so now is the time to resist and refuse to open ourselves up to unprecedented degrees of vulnerability towards the state and corporations. Doing it voluntarily while it is still rather cheap is a bad idea.
Re: A hackable AI assistant using a single SQLite table and a handful of cron jobs
#27This made me think: what if my little utility assistant program that I have, similar to your Stevens, had access to a mailbox? I've got a little utility program that I can tell to get the weather or run common commands unique to my system. It's handy, and I can even cron it to run things regularly, if I'd like. If it had its own email box, I can send it information, it could use AI to parse that info, and possibly se…
I’ve been thinking lately that email is a good interface for certain modes of AI assistant interaction, namely “research” tasks that are asynchronous and take a relatively long time. Email is universal, asynchronous, uses open standards, supports structured metadata, etc.
If you don't need to have the lowest possible latency for your work and you're happy to have threads die then it's better than any bespoke solution you can build without an army of engineers to keep it chugging along.
What's even better is that you can see all the context, and use the same command plane as the agents to tell them what they are doing wrong.
Re: A hackable AI assistant using a single SQLite table and a handful of cron jobs
#28Re: A hackable AI assistant using a single SQLite table and a handful of cron jobs
#29For me, that is an extremely low barrier to cross.
I find Siri useful for exactly two things at the moment: setting timers and calling people while I am driving.
For these two things it is really useful, but even in these niches, when it comes to calling people, despite it having been around me for years now it insist on stupid things like telling me there is no Theresa in my contacts when I ask it to call Therese.
That said what I really want is a reliable system I can trust with calendar acccess and that is possible to discuss with, ideally voice based.
Re: A hackable AI assistant using a single SQLite table and a handful of cron jobs
#30> cron job which makes a call to the Claude API