I'd say it's because we're tasking ourselves with dumb stuff. No one half-asses building a shelter that keeps their family alive, or throwing a new favorite bowl on the pottery wheel. But instead of that we're writing posts for Facebook etc etc so we can (???) profit. So of course we want bots to do this all this dumb stuff, and of course we get dumb results.
For some things, yes. But I'm half-assing some really cool stuff right now. Made a scraper to pull my city's meeting minutes, agendas, recordings, made transcripts. Regex for "Flock", found every mention, passed those files into a cheap model (DeepSeek V4), had an understanding of who in my city is down with building the surveillance state and who isn't. I've got research on everyone, and had emails drafted for each one based on what they said. Quotes and figures and all. I lightly polished each email and fired 'em off. Already got some replies back. Plenty more in the quiver too (pulled and analyzed CSVs of FOIA'd datasets).
If they're gonna spy on me with AI cameras, I can oppose them with AI research. :)
Did you use some stuff like https://github.com/CouncilDataProject or roll your own? Been curious about how to integrate local knowledge like this since local news seems to have lost the niche.
I rolled my own. I hadn’t heard of this one, but I looked into stuff like OpenStates (now privately for-profit owned, ugh). My city just uses a Wordpress site so it’s structured enough. I’m looking at building something to ingest cities with Granicus and one other big local government meeting recorder via API whose name I forget. That should get decent coverage. There’s no way to catch the long tail of every local government’s recording process. Some cities people will just have to do manually. But it’s easy enough with LLM help.
> I've got research on everyone, and had emails drafted for each one based on what they said. Quotes and figures and all.
Please tell me you did the work to validate that the quotes and figures were not made up by the cheap model. These things make stuff up all the time, you absolutely cannot rely on them without validating the output yourself.
Yep, I manually listened to the meeting recordings (easy to find the spots based on the transcript timestamps) for any quotes. There are also meeting minutes and agendas with supporting docs to corroborate against (e.g. for dollar amounts). They really don’t make stuff up all the time if you root them in data.
Nope, I used a minute fraction of the technology they have, along with open records as is my right in this country, to stand up for my Fourth Amendment right to travel without creeps stalking my every move. I need to make my specific framework a bit more generic and then I'll put it here on HN. Or just offer a platform where people can bring an OR key and it can run on their city.
Citizens monitoring their government is literally THE foundation of democracy (ok, maybe voting comes before it, but then you have to monitor who you voted for to see if they’re doing what you voted for).
I think this is a larger question we should be asking. YES, we can build this world: a world where robots do our chores, serve our coffee, check us out at the grocery store, and let the AI agents do the parts of our jobs we love.
But SHOULD we? With great power comes great responsibility - and I'm getting the impression we're (quickly) building a world that isn't very fun to live in. We technically have a choice here - DO we want bots writing our prose and responding to our customer service inquiries?
I'm of the opinion that "true art"/cultural artifacts can't be automated by definition, as they derive their value from the human experience embedded in them by their creators.
OTOH, I think we absolutely SHOULD automate necessary "drudgery" type work wherever we can, but we're going to need a radical reconceptualization of how we distribute the spoils of economic productivity as a result.
Unfortunately, I think the type of reconceptualization we'd need would entail a complete overhaul of many long-established and deeply-internalized concepts (rights and duties of ownership of intellectual and private property, decoupling of identity and occupation, etc.), and from everything I've seen, that will be a long and painful process assuming it's even achievable. (Especially in the US, where decades of pro-business messaging has yielded a culture that equates income-earning ability/entrepreneurial success with individual human worth. I really struggle to imagine a path toward unwinding that, but there's little chance it'll be a smooth ride.)
I remember a book I read as a pre-teen, 40 or so years ago, about a kid who wanted to be "perfect". A wear a tree of broccoli on a string around your neck to learn how to overcome embarrassment. A perfect person never makes mistakes, and the best way to not make mistakes is to not do anything. Similar "requirements" of perfection and their expression are presented. The kid eventually finds himself in an empty room, by himself, doing nothing, wearing broccoli. Perfection was achieved, but at the cost of an extremely boring life.
Knowing the cost of home ownership, it’s not unlikely to imagine the reported damages are well within what he’s asking. Given that repair work, filing paper with the courts, etc is a major PITA, if this guy was just looking for a payout you’d think he’d ask for a lot more.
Perhaps it's just regional, but I've been noticing more and more people saying "chat" to describe ANY ai chat interface including ChatGPT. They might have a Kleenex problem on their hands.
Doubtful these clowns even have commercial insurance for these rentals. What a deceitful and dangerous way to build a business - to save (what?) a few thousand per rental?
I had the opportunity to live with Drew back in 2006 when he, I, and another pair of YC founders Adam and Matt were living together and hacking away at our own startups in Cambridge. I remember Drew being a hard worker, humble, and a genuinely nice guy. It's probably self indulgent to claim that we all inspired him to eventually shift gears to Dropbox and apply to YC - but what a path it's been for him! I've always felt inspired by his meteoric innovation in cloud storage - Dropbox paved the way for all our modern cloud storage systems. We've fallen out of touch over the years, but I wish him well on whatever comes next.
Love the concept! Some feedback: I went to sign up to give it a go, but the set up process left me feeling a bit untrusting - so I backed out for now. I'd prefer more explanation about what to expect, what I will get, how it is safe, etc before asking me to run a prompt.
Right now, the prompt will enumerate all the services and install the OpenTelemetry SDK (https://opentelemetry.io/) in each service.
Then for every service, the skill will make sure that:
- Every time something breaks and an operator needs to take a look, there's an error log
- All important steps in a process emit info/debug logs (so that an issue can be investigated)
- Operations are covered with spans with relevant attributes.
- Cost (LLM tokens), API performance (latency/RED), tenant activity (cost/usage per tenant) are covered by metrics so that you can use Superlog MCP to build cool dashboards.
For most common stacks like NextJS, FastAPI, React Native/Expo etc. we have a custom skill that explains the best practices for this specific technology. For all the other stacks we ask the agent to use general best practices.
We have evals for all custom skills where we start from a starter project, run the agent with the skill and use LLM-as-a-judge to compare it to a human-written 'golden patch'.
In general, we try to:
- minimize diff, so that the instrumentation is easy to review
- make small chunks of additive diffs vs huge indents / moving logic around
- minimize new dependencies
- use well-supported and audited OTel SDKs vs custom libs
I agree with this sentiment. And it's hard to change. But there are plenty of examples of people exiting the normalized system and choosing a different life. Even small changes can make a big impact on mental health, like stopping reading the news.
But I'd encourage the author to consider what setting an example might look like for them. What does a less complicated life look like? Then live it, and eventually, more will follow.
[BestInterest](https://bestinterest.app) helps coparents find peace by automatically filtering out anything that isn't child-focused from their coparent's messages. Ensures court order compliance and reduces conflict.
It seems strange to me that our laws allow someone to declare personal bankruptcy to avoid paying on liabilities, while somehow maintaining interests in other companies…
resulting in that weird situation where another of his companies tries to buy the “bankrupt” company? (If you didn’t read the article, the only other bidder against the Onion was one of Alex’s own companies)
Jones is a grifter, but I almost admire his brazen attempts here. If he is successful in any way, he is doing a service to point out the flaws in the systems.
reply