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

111–120 of 183 posts

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

#111

Post by simonw »

triyambakam wrote: post #109
simonw wrote: post #87

Earlier quoted context omitted.

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/

> Yes. Trusting them is my competitive advantage. I don't see what that is supposed to mean. What does that give you?

It gives me the ability to take advantage of the best available models without holding back for fear of them abusing my data.

The alternative is either not using this stuff at all or restricting myself to the much less capable local models.

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

#112

Post by Arcuru »

jredwards wrote: post #104

I've been kicking around idea for a similar open source project, with the caveats that: 1. I'd like the backend to be configured for any LLM the user might happen to have access to (be that the API for a paid service or something locally hosted on-prem). 2. I'm also wondering how feasible it is to hook it up to a touchscreen running on some hopped-up raspberry pi platform so that it can be interacted with like an Ale…

I also want an OSS framework that lets me extend it with my own scripting/modules, and is focused around being an assistant for me and my family. There's a shared set of features (memory storage/retrieval, integrations to chat/email/etc interfaces, syncing to calendar/notion/etc, notifications) that should be put into an OSS framework that would be really powerful.

I also don't have time to run such a thing but would be up for helping and giving money for it. I'm working on other things including a local-first decentralized database/object store that could be used as storage, similar to OrbitDB, though it's not yet usable.

Mostly I've just been unhappy with having access to either a heavily constrained chat interface or having to create my own full Agent framework like the OP did.

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

#113

Post by triyambakam »

simonw wrote: post #111
triyambakam wrote: post #109

Earlier quoted context omitted.

> Yes. Trusting them is my competitive advantage. I don't see what that is supposed to mean. What does that give you?

It gives me the ability to take advantage of the best available models without holding back for fear of them abusing my data. The alternative is either not using this stuff at all or restricting myself to the much less capable local models.

But how is that a personal advantage? Who are you in competition with against yourself? Maybe I'm parsing competive advantage in a different context than you mean.

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

#114

Post by nullwarp »

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 built up an AI Agent using n8n and email doing exactly this. Works great and was surprised I'd not seen any other place kicking the idea around.

Probably my favorite use case is I can shoot it shopping receipts and it'll roughly parse them and dump the line item and cost into a spreadsheet before uploading it to paperless-ngx.

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

#115

Post by kovek »

jredwards wrote: post #104

I've been kicking around idea for a similar open source project, with the caveats that: 1. I'd like the backend to be configured for any LLM the user might happen to have access to (be that the API for a paid service or something locally hosted on-prem). 2. I'm also wondering how feasible it is to hook it up to a touchscreen running on some hopped-up raspberry pi platform so that it can be interacted with like an Ale…

Why not use a smartphone for the user interface?

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

#116

Post by simonw »

triyambakam wrote: post #113
simonw wrote: post #111

Earlier quoted context omitted.

It gives me the ability to take advantage of the best available models without holding back for fear of them abusing my data. The alternative is either not using this stuff at all or restricting myself to the much less capable local models.

But how is that a personal advantage? Who are you in competition with against yourself? Maybe I'm parsing competive advantage in a different context than you mean.

I guess I'm competing against other humans at living a fulfilling, enjoyable life?

I don't take that competitive advantage particularly seriously, which is why I invest so much effort giving away what I've learned along the way for free.

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

#117

Post by frainfreeze »

dostick wrote: post #110
panki27 wrote: post #107

Earlier quoted context omitted.

You might want to take a look at SillyTavern. Supports multiple backends, accepts voice input, and has a plugin system.

I keep hearing about it, but never got to check out, the name suggests that it may be waste of time. Maybe it’s a fantastic project but name lets it down?

You are on Hacker News, typing on Apple, listening to Daft Punk, reading an article about Steven, the AI butler hosted on Val Town, comment chain you're replying to talks about using self hosted models (probably llama) and Raspberry Pi, yet SillyTavern is the name that trips you up?

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

#118

Post by fallinditch »

panki27 wrote: post #107
jredwards wrote: post #104

I've been kicking around idea for a similar open source project, with the caveats that: 1. I'd like the backend to be configured for any LLM the user might happen to have access to (be that the API for a paid service or something locally hosted on-prem). 2. I'm also wondering how feasible it is to hook it up to a touchscreen running on some hopped-up raspberry pi platform so that it can be interacted with like an Ale…

You might want to take a look at SillyTavern. Supports multiple backends, accepts voice input, and has a plugin system.

Having multiple backends can be a good approach, with various LLMs for different specialized tasks. I haven't tried it yet but WilmerAI is an option for routing your inputs to the appropriate LLM, works well with SillyTavern.

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

#119

Post by xp84 »

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 "Must also use our walled garden ecosystem for email, calendars, phones, etc" -- is an embarrassment, only obscured by the two companies' shared lack of ambition to apply "AI" technology to the 'solved problem' areas that amount to various kinds of summarization and question-answering.

If ever there was a chance to threaten either half of this lumbering, anticompetitive duopoly, certainly it's related to AI.

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

#120

Post by dcre »

xp84 wrote: 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.
Post reply on HN