Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

A hackable AI assistant using a single SQLite table and a handful of cron jobs

geoffreylitt.com

Post reply on HN
Print view View original

81–90 of 183 posts

Re: A hackable AI assistant using a single SQLite table and a handful of cron jobs

#81

Post by IanCal »

bob1029 wrote: post #9
mbil wrote: post #6

Earlier 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.

This is how I initially pitched an AI assistant in my last shop. It is a lot cheaper to leverage existing user interfaces & tools (i.e., Outlook) than it is to build new UIs and then train users on them.

Also an email that comes back a minute later feels fast. A chat that types at the same speed feels slow.

Re: A hackable AI assistant using a single SQLite table and a handful of cron jobs

#83

Post by squireboy »

" Initially, Stevens spoke with a dry tone, like you might expect from a generic Apple or Google product. But it turned out it was just more fun to have the assistant speak like a formal butler. "

Honestly, saying way too little with way too much words (I already hate myself for it) is one of the biggest annoyances I have with LLM's in the personal assistant world. Until I'm rich and thus can spend the time having cute conversations and become friends with my voice assistant, I don't want J.A.R.V.I.S., I need LCARS. Am I alone in this?

Re: A hackable AI assistant using a single SQLite table and a handful of cron jobs

#84

Post by triyambakam »

simonw wrote: post #77
triyambakam wrote: post #74

First: > I’ll use fake data throughout this post, beacuse our actual updates contain private information but then later: > which makes a call to the Claude API I guess we have different ideas of privacy

What makes you think sending data to the Claude API is a breach of privacy? Do you not trust them when they say they won't look at or train on your data?

No I don't. Do you?

Re: A hackable AI assistant using a single SQLite table and a handful of cron jobs

#86

Post by bob1029 »

dkdcwashere wrote: post #11
mbil wrote: post #6

Earlier 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

> trying to build a company around this

I am still very open to this one. An email-based, artificial coworker is so obviously the right way to penetrate virtually every B2B market in existence.

I don't even really want to touch the technology aspects. Writing code that integrates with an LLM provider and a mailbox in E365 or Gmail is boring. The schema is a grand total of ten tables if we're being pedantic about things.

Working with prospects and turning them into customers is a way more interesting problem. I hunger for tangible use cases that are actually compatible with this shiny new LLM tooling. We all know they're out there, and email is probably the lowest friction way to get them applied to most businesses.

Re: A hackable AI assistant using a single SQLite table and a handful of cron jobs

#87

Post by simonw »

triyambakam wrote: post #84
simonw wrote: post #77

Earlier quoted context omitted.

What makes you think sending data to the Claude API is a breach of privacy? Do you not trust them when they say they won't look at or train on your data?

No I don't. Do you?

Yes. Trusting them is my competitive advantage.

I've also been following Anthropic pretty closely for the last two years and I've seen no evidence that they would break their principles here and plenty of evidence of how far they go to respect the privacy of their users: https://simonwillison.net/2024/Dec/12/clio/

Re: A hackable AI assistant using a single SQLite table and a handful of cron jobs

#88

Post by kswzzl »

squireboy wrote: post #83

" Initially, Stevens spoke with a dry tone, like you might expect from a generic Apple or Google product. But it turned out it was just more fun to have the assistant speak like a formal butler. " Honestly, saying way too little with way too much words (I already hate myself for it) is one of the biggest annoyances I have with LLM's in the personal assistant world. Until I'm rich and thus can spend the time having cu…

I'm praying every day for TARS if I'm being honest.

Re: A hackable AI assistant using a single SQLite table and a handful of cron jobs

#89

Post by cosbgn »

dogline wrote: post #4

This 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…

Try https://unfetch.com (I've built it). It can handle both inbound and outbound emails

Re: A hackable AI assistant using a single SQLite table and a handful of cron jobs

#90

Post by sdsd »

dogline wrote: post #4

This 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 made an AI assistant telegram bot running on my Mac that runs commands for me. I'll tell it "Run ncdu in the root dir and tell me what's taking up all my disk space" or something and it converts that bash and runs it via os.system. It shows me the command it created, plus the output.

Extremely insecure, but kinda fun.

I turned it off because I'm not that crazy but I'm sure I could make a safer version of it.

Post reply on HN