In the case of HA, the agent is receiving ambiguous natural language requests and converting them into HA MCP calls. I can open the HA app and press buttons, sure, but the agent can reason over time about patterns of water/electricity use, provide natural language feedback, push back on my automation ideas with counterexamples from sensor logs - and all the sensors in the home and on the phones carrying the companion app are rich signal sources for an agent. It unlocks neat tricks like when our babysitter comes over the front door agent can alert her if there’s a water leak and walk her through shutting off the water to the house or locate the backup key for her. It can DM me when someone rings the doorbell and carry on a different conversation with STT depending on if it is a person wearing a uniform or holding a clipboard for example thanks to Frigate and some custom vision ingestion with Qwen 3 VL.

Regarding the torrents, that agent keeps track of my ratios on the private trackers and I can give it natural language feedback about what I did or didn’t like about a show or movie and it will suggest alternatives, find them on a private tracker, download them, unpack them, and ingest them in the library for me, keeps track of the families like and dislikes and suggests media to watch together, watch private trackers for open invites or interview slots and take the knowledge interviews for me on IRC, deduplicate downloads and hunt for releases with minimum quality standards etc. one of my first tasks for it was replacing my music collection that got damaged when my external hard drive got dropped with no backup and I had to get it extracted in a clean room. Lots of rare lifetime accumulated mp3s gone - mostly recovered now. Searching for replacements would have been a long slog so I automated it.

To your point some of these things could be done by deterministic python scripts and in fact the agents write those to save inference costs later and most of this stuff I could do by siting on my computer an clicking on stuff and reading - the point is that the agents constitute a natural language control surface to trigger all of those actions for me automatically so I can just send a couple chats to a discord bot and it will be done a few minutes later. I’m a busy person I dunno if you can relate. Busy career, got a family to support, parenting obligations, no time to hang out playing video games any more sadly. Building stuff takes time and effort and you have to learn and read about how to do it or pay someone else to do it for you so I was stuck on the easy convenience of windows and Netflix and Amazon/kindle etc. Not anymore! It started with having to install docker desktop to get OpenClaw working and then pretty fast I figured out pretty much everything I wanted to do now that was not work related is better done on Linux and better done self hosted. I would never have gotten over that hump without LLMs.

So one thing that’s really helpful to automate is checking all the repos for my self hosted stacks and testing/validating/deploying new versions when they come out. They’re also good at writing helper scripts in Python to automate things deterministically so I don’t have to keep using LLMs for it. There’s an agent that is focused on learning and managing my wife’s school schedule, ingests her grades and syllabi and reviews her homework and makes helpful 10 minute podcasts on concepts she’s struggling with in her engineering program (not notebookLM, a self hosted lookalike), there’s a domestic agent that accepts uploads of grocery receipts and does our meal planning and schedules time for meal prep and chores and divides it up between us and the kids depending on everyone’s calendars, there’s a home media agent that manages qbittorrent and my ratios on private torrent trackers and files new manga or TV shows or movies ebooks audiobooks etc in the right library when new things come out we might like, viewing/reading/watching metadata tells the agent what content is popular to queue up in the next sweep - there’s a home assistant front door agent that can make automations or report sensor state or trigger scenes or entities in the general text channel of our home discord server and can tell me where my phone or keys are thanks to ESPresence being able to use cheap ATOM esp boards throughout the house (tiny little USB powered things with Bluetooth and wifi) to triangulate the location of any watched Bluetooth device or tracker tag in 3 dimensions through floors and walls - what else…there’s a home security red-team agent that looks for security holes in my cloudflare tunnel/kv worker/tailscale/caddy/protonVPN routes and monitors a cyber security RSS feed, I have a job/market research bot that ingests another RSS feed for news relevant to my industry and organization and gives me email and voice briefings on new regulations and corporate leadership signals, stuff like that. What else… there’s a game dev bot where my kids can talk to a discord bot that routes to a game dev agent that has Godot MCP and Unity MCP and renpy MCP and lots of other fun tools like Roblox MCP and Minecraft to make custom games we can deploy on Google cloud for their friends to play (my daughter is really into visual novels for some reason I don’t get it) - all sorts of fun stuff. Discord is kind of the family shared interface and then the privileged control planes are routed to my phone through tailscale and the home media server stacks are exposed through cloudflared.

Yes, with OpenClaw I can expose my agents via discord apps on my home discord server, I like that route because of the rich media and UI options (agents can give me drop down selector lists and approve/reject buttons). I have two 24gb Nvidia cards for local models usually Qwen, Mistral, and nemo based models for different purposes. I can chat with the agents anywhere I’m logged into discord and I expose privileged control surfaces and nodes via tailscale and family/shared endpoints via caddy and cloudflared

You can just turn off a data center. How are you gonna turn off a thousand refrigerators?

Common misconception we actually use all of our brains, people just liked to say we only use 2% of it because they didn’t like to admit they couldn’t figure out what the other 98% did a few decades ago.

Nothing ironic about that. Thanks to OpenClaw and open weights AI models I started self hosting and figuring stuff out that would have made me frustrated and quit years ago. I have home assistant running on bare metal on a mini PC, a NAS with custom bios, migrated everything away from windows, Kavita for ebooks, jellyfin for music and video, nightscout to ingest my wife’s insulin pump data, and some fun custom sidecars that tie together some nifty automations like automatically diarizing and transcribing voice notes of meetings from my phone without having to pay a subscription fee - latest projects have been a local sync point for logseq, kitchenowl, and nextcloud - super productivity android app and caldav and the to-do lists in home assistant. I never would have had the time to figure all this out with my full time job and parenting but I can cut the cord to all my subscription services and I look at things a new way now. I solve my own problems now when before I would just look for a way to buy a solution. I bought bunk beds for the kids but the bottom bunk didn’t come with slats and I couldn’t find the right size so I went to home Depot and built my own with instructions from my ops agent. I had a fun idea to make an e-ink display sign for my office door that shows what town I’m currently in and what my current MS outlook calendar block is and when it’s over. I never played with Arduino before and now I’m hooked. It gets me over that first execution hump. Sure I break stuff and have to figure out how to put it back together again but that’s part of the fun. I finally found a way to learn stuff that works for me, you know, comes naturally. It’s like I’ve been waiting my whole life for this ever since growing up seeing people using computers via natural language in Star Trek. It extends to my work. The data I need is gated behind ticketing systems of business intelligence professionals who don’t have the time or inclination to give me what I need so hey looks like copilot basic is great and m-code, guess I don’t need BI analysts after all. Sucks for them.

Health insurance companies don’t have to disappear overnight they can just be seized under eminent domain for fair market value of their land and office supplies.

Read the article. A MoE model distributed between multiple devices can function just very slowly. It doesn’t need to translate Icelandic poetry just execute narrowly scoped actions it was specifically trained on.

Weird so now FBI agents are going to gently cuddle the criminals until they tap out?

Man you have a real low bar for idealism. We could be… You know… Seizing the means of production and building a stateless and classes worker’s utopia. Fully automated luxury gay space communism. Use your imagination my dude.

Well they aren’t voting on him to be Pope

Government administered healthcare has better outcomes and less administrative overhead than privately administered healthcare. Look at privatized firefighters for another example. Government is always on the forefront of messy expensive and complex systems and yes it could be improved but if half of it wasn’t trying to deregulate the other half out of existence we could probably bring some more resources to bear on the problem more efficiently.

The problem is that profit seeking enterprise explicitly doesn’t serve human values and that’s by design.

Also psychiatric commitment isn’t necessarily forever and has a restorative focus.

Just levying fines and imposing jail sentences doesn’t go far enough, it’s a 19th century solution to a 21st century problem.

Corporate personhood and limited liability need to be abolished and private enterprise needs to be re considered from first principles for the modern era.

It corporations are people, there needs to be a death sentence and involuntary psychiatric commitment .

My friend, the meta analysis has been done. Consult a medical librarian. This is not controversial at all.

Regret rate is lower then joint replacement surgery and chemotherapy.

And our university hospital folded and isn’t answering questions about what deal they made with the feds.

Some features of the app claim to require shizuku, maybe the app itself is lying to me?

MyAnonymouse is fantastic. Open invites every month or so, easy interview if you read the rules, great perks with small single digit donations, well worth it. Audiobooks, radio shows, novels, textbooks, you name it. No porn but plenty of adult stuff too. Some recent comics series I got turned on to through there - Die, East of West, Monstress, Sunstone, The Wicked and The Devine, and much more.

I need it to run keymapper which is very cool and lets me map Bluetooth keyboard combinations to map them to app UI elements. Also shizuku-mcp let’s my OpenClaw stack remotely operate my mobile device which is also lots of fun

Look at the source code. If it looks clean and is commented intelligibly, it’s synthetically generated