Live data from Hacker News

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

geoffreylitt.com

131–140 of 183 posts

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

#131
post #6
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’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.

I'm building something similar. See my comment the OP above:

https://threadwise.app

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

#132
post #81
post #9

Earlier quoted context omitted.

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.

I'm building something similar. See my comment the OP above:

https://threadwise.app

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

#133
post #122

Earlier quoted context omitted.

The Apple walled garden argues against you here. There are at least 20 million families in America where this holds true: • Everyone in household uses an iPhone • Main adult family members use iCloud Mail or at least use Apple Mail to read other mail • Family members use iCloud contacts and calendars • USPS Informed Delivery could be used (available to most/all US addresses) • It can be ascertained what ZIP code you'…

Not every one of those families would find the same set of features helpful, so you have to make calls about what's worth developing and what isn't. Making those calls is very difficult because it's tricky to gather data about what will be used and appreciated.

And whatever they are doing is clearly working well. /s

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

#134

" 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…

You can just read and write the notebook directly with ordinary calendar/todo-list UIs and get 99% of the utility without an LLM. I'm not really seeing value in the LLM except the butler voice? It is just reading the notebook right? E.g. they ask the butler to remember a coffee preference, but then that's never used for anything?

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

#135
post #86

Earlier quoted context omitted.

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 thin…

> Working with prospects and turning them into customers is a way more interesting problem.

Agreed. That's also the hardest part, and where most value is created.

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

#136
post #28

This is probably naive and looking forward to a correction; isn't sending your info to Claude's API (or really any "AI API") is a violation of your safeguarded privacy data?

Using AWS Bedrock is the choice I've seen made to eliminate this problem.

How does bedrock eliminate this problem?

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

#137
post #120
post #119

I don't know if I love this more for the sheer usefulness, or for the delightful over-the-top "Proper English Butler" diction. But what really has my attention is: Why is this something I'm reading about on this smart engineer's blog rather than an Apple or Google product release? The fact that even this small set of features is beyond the abilities of either of those two companies to ship -- even with caveats like "…

There’s actually a good answer to this, namely that narrowly targeting the needs of exactly one family allows you to develop software about 1000x faster. This is an argument in favor of personal software.

yes which vibe coding enables.

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

#138
post #90
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.

Easy fix, just pipe the commands to a 2nd LLM and ask "will this command delete my home directory (y/n)"

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

#140

Earlier quoted context omitted.

Using AWS Bedrock is the choice I've seen made to eliminate this problem.

How does bedrock eliminate this problem?

You aren't sending your data to Anthropic- no one has access to what you send except you. If you use private link, it doesn't even leave your vpc.
Post reply on HN