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

171–180 of 183 posts

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

#171

Post by theshrike79 »

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?

SillyTavern started up as a roleplaying model

As in "you meet a person at a tavern" and then you start chatting.

People provide different personalities to the project, sometimes with avatars and I think some can even change avatars based on their "mood".

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

#172

Post by theshrike79 »

Arcuru wrote: post #112
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…

So something like MCP, but with a slightly different, more focused, scope?

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

#173

Post by theshrike79 »

jkestner wrote: post #33
eitland wrote: post #29

> It’s rudimentary, but already more useful to me than Siri! For 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…

I've had the same issues of decay. I used to be able to say "call Mom" but now it will call some kid's mom who I have in Contacts as "[some kid's] mom". What is the underlying architecture that simple heuristic things like this can get worse? Are they gradually slipping in AI?

I always say "call my mom" and it'll pick it up from contacts -> relationships correctly

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

#174

Post by theshrike79 »

philsnow wrote: post #126
kylecazar wrote: post #50

I like the idea of parsing USPS Informed Delivery emails (a lot of people I encounter still don't know that this service exists). Maybe I'll make something to alert me when my checks are finally arriving!

This part was galling to me; somewhere in the USPS, the data about what mailpieces/packages are arriving soon exist in a very concise form, and they templatize an email and send it to me, after which I can parse the email with simple+brittle regexes or forward the emails to a relatively (environmentally-)expensive LLM or so.... but if they'd made the information available with an API or RSS feed, or attached the json…

In Finland our own USPS (Posti) has their own mobile application that does delivery notifications. They've been directing users towards the app pretty heavily and deprecating other interfaces.

You can still get the parcel ID and use a public-ish web API to get tracking information on a rough level ("in transit", "being delivered") without exact address information.

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

#175

Post by theshrike79 »

larsonnn wrote: post #49

I argue that this kind of tools are fun to play but in the end is it really helpful? I start my day like every day and on work I just check the calendar. My private calendar has all Information i need. Where is the gap where an Assistent makes sense and where we are just complicating our lives?

Now think of this at a family level. You have 2+ people with shared calendars and events.

Do you sit down as a family every morning and go through your calendars and sync up?

Or would it be better to have an automated summary posted to the family Telegram channel with "Bob has a dentist today at 1300, which overlaps with Mia's football practice, so Sara has to pick her up. Also it's going to rain so prepare accordingly."

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

#176

Post by theshrike79 »

redman25 wrote: post #67
stunnAR wrote: 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?

You could always run your own server locally if you have a decent gpu. Some of the smaller LLMs are getting pretty good.

Also M-series Macs have an insane price/performance/electricity consumption ratio in LLM use-cases.

Any M-series Mac Mini can run a pretty good local model with usable speed. The high-end models easily compete with dedicated GPUs.

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

#177

Post by theshrike79 »

pmdr wrote: post #103

Well it's probably ahead of Apple Intelligence in usefulness and functionality. We should see more things like this.

This is doing what Apple Intelligence was advertised as doing. Gather data from multiple sources and aggregate it.

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

#178

Post by xp84 »

simonw wrote: post #162
fmbb wrote: post #155

Earlier quoted context omitted.

The thing that is standing in their way is probably that nobody is willing to pay for this what it costs to run.

Doesn't look very expensive to me. An LLM capable of this level of summarization can run in ~12GB of GPU-connected RAM, and only needs that while it's running a prompt. The cheapest small LLMs (GPT-4.1 Nano, Google Gemini 1.5 Flash 8B) cost less than 1/100th of a cent per prompt because they are cheap to run.

Yes! And also, Apple loves selling expensive hardware and has zero shyness asking people to pay a few thousand bucks to buy into part of their ecosystem.

They could easily offer an on-prem family 'AI' product that you plop in your house and plug into your router, and does all AI processing for the whole family, and uses a secure VPN to connect to any of your devices outside the LAN.

If such a product delivered JUST what this guy's cool hack provides, and made Siri not a stupid piece of sh*t for my family, I'd buy it for $1999 even if I knew it cost Apple $700 to make.

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

#179

Post by stunnAR »

redman25 wrote: post #67
stunnAR wrote: 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?

You could always run your own server locally if you have a decent gpu. Some of the smaller LLMs are getting pretty good.

Yes - of course. That's been my experience with "ultimate" privacy.

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

#180

Post by larsonnn »

theshrike79 wrote: post #175
larsonnn wrote: post #49

I argue that this kind of tools are fun to play but in the end is it really helpful? I start my day like every day and on work I just check the calendar. My private calendar has all Information i need. Where is the gap where an Assistent makes sense and where we are just complicating our lives?

Now think of this at a family level. You have 2+ people with shared calendars and events. Do you sit down as a family every morning and go through your calendars and sync up? Or would it be better to have an automated summary posted to the family Telegram channel with "Bob has a dentist today at 1300, which overlaps with Mia's football practice, so Sara has to pick her up. Also it's going to rain so prepare according…

When you are sharing the calendar it will be synced on every device. And yes as a family we go through all dates on Sunday for the next week.

Which is a nice time with the family we are sitting drinking coffee also with other family members.

When you Lack so much organization skills the AI would never get the data to write you this.

Post reply on HN