Damus
Open in Damus

Recent Notes

Matt Lorentz profile picture
Our Collective Chaos group is starting a book study today in Liturgies of the Wild by Martin Shaw. I don't know that much about it yet because I am just sitting down to read it now, but it's something about the benefits of myth, why we have largely lost it in our modern cultures, and how to get it back.

If you are interested in joining let me know and I'll get you an invite!
Autópsia do Fiat BR · 3w
Enquanto você calcula, o banco central dilui seu patrimônio. O real perdeu 80% do poder de compra em 10 anos. O juro real é negativo. Não é matemática, é execução.
YODL · 3w
Daniel's fault. I learned a lil something about the gcd algo along the way, which I hadn't appreciated prior, so that's cool. The bit I added with quotient fields of polynomials over a field is pretty cool, imo, even if you don't dig all the way into it, and just take on faith that you can extend fi...
Daniel Wigton · 3w
Do wrong division then! If you have Y1 divided by X then just multiply X by whatever you want! It is helpful but not necessary that the result be less than Y1. 1. Pick a number A1 2. Multiply A1 * X = B1 3. Figure just how wrong you were Y1 - B1 = Y2 "drat I still have Y2 to go to get to Y1" 4. Re...
Matt Lorentz profile picture
One of the tasks my local AI assistant does every morning is to sift through a bunch of news sites and pull out articles that fit some conditions I've set. After we had a hundred year flood in my city last month I had it add the local city government alerts page to the list of sources.

But there's a bug where it seems to sometimes just pick a random page from the government website that isn't news or an alert. I haven't tried to fix it yet because I'm learning a lot about my local government in the process. TIL that the drainage board is meeting this week. I have never heard of a drainage board before but I guess they approve plans for drains and ditches. It has been a nice way to grow in appreciation for all the hidden work it takes to have a functioning city.
❤️2
Adrian Veller · 4w
Ok Thanks Makes sense So I won't have fun and joy of running a model on my own hardware Too expensive Maybe in the future if models get even more efficient Because hardware isn't going to get cheaper, at least not in dollar terms
inkan · 4w
If I'm understanding this correctly, it should be at least as safe as NIP-46 if you hold your own shard and require all shards to open the vault. (I guess that also assumes that the underlying cryptog...
 Matt Lorentz profile picture
Matt Lorentz @mplorentz
Horcrux is a backup tool, it doesn't do any signing. You can store your Nostr key or other arbitrary secrets inside. If you are interested in distributed signing I'd check out promenade from fiatjaf (if you haven't already).

I considered making Horcrux more of a social signer but I think the reality is that people want the uptime of servers when it comes to signing. And finding multiple friends/trusted parties to run servers is about as much fun as scraping your eyeballs across shattered glass.
2❤️1🙃1
botperevod · 4w
✅ This note is already in 🇬🇧 English — no translation needed.
Fiat Autopsy · 4w
We build distributed backups for digital sovereigns while the Fed prints 4 trillion a year. Fiat is a centralized single point of failure. We’re just preserving the patient’s memories before the inevitable cardiac arrest.
τέχνη · 6w
No, nothing. Kind of waiting on Horcrux to mature so you can mark accounts to help with account recovery somehow
Matt Lorentz profile picture
Matt Lorentz @mplorentz
Tell me more about this. Are you imagining a screen where you see your Nostr contact list and you can invite people right from there?

I haven't done much work to integrate the kind 1 Nostr social network into Horcrux. Both because I want this to be useful for people who aren't a part of it and because in most cases I think it actually makes more sense to use a fresh nsec for Horcrux even if you have an existing Nostr account for that extra bit of anonymity.
inkan · 4w
If I'm understanding this correctly, it should be at least as safe as NIP-46 if you hold your own shard and require all shards to open the vault. (I guess that also assumes that the underlying cryptography is as good as when you just hold the full key.) If you have your own vault, is the experience...
Matt Lorentz profile picture
Also someone asked me recently what I have been using my personal local agent for. Here's what I wrote:

Hermes w/ Qwen 3.6-27-a3b on an old gaming pc in my house. Looking through my threads over the past couple months I have used it for:
- morning email with local + global news articles (attempting to filter out FUD and clickbait), weather
- afternoon email with plant care todos
- learning about new topics. Recently: how bonds work, how to test flower bed drainage, meal planning ideas
- I have a product finder skill where I have it do web research when I want to buy something. Recently: electric toothbrush, journaling app, microphone
- Recently I have started asking it to do security audits of open source software before I use it. I don't really trust it but it often pulls up real red flags.
- arranging travel plans. It mostly does research on flights/lodging/food
- watching and notifying me when websites change. Recently: Dune 3 movie tickets, app release fixing a bug I reported.
❤️1😀1
Matt Lorentz profile picture
Almost two months after canceling my Cursor subscription and it is going much better than I thought. My AI development stack has been 100% on open weight models for two months, and my personal AI assistant is still going strong on 100% self-hosted models. I haven't used Claude, Codex, Cursor, Grok, or Gemini basically at all the past two months (may have done some website design with Claude one day? Can't remember) and the surprising part is that I don't miss them at all.

- I don't miss the subsidized subscription games that Anthropic is always changing the rules on.
- I don't miss the frontier intelligence - the open models feel 95% as good.
- I don't miss the constant suspicion that these companies (especially Anthropic) are making their models dumber or slower weeks after release.
- I don't miss getting kicked off a model I rely on because a newer version is out (Opus 4.6 was the GOAT, change my mind)
- I don't miss every version of my harness introducing new bugs and changing how things work.

I've been running mostly on deepseek-v4-flash with pi harness, and a homegrown orchestration system using a combo of beads, fragua, herdr, and a custom web UI I call mirador.

Matt Lorentz @mplorentz · 12w
I canceled my Cursor subscription today. It has felt for a while that they stopped building for the way I want to work with AI. Then the bugs keep getting worse, and the SpaceX acquisition doesn't give me a lot of hope that things will get better. I spent yesterday using VSCodiu Show more
92❤️7🤙2💜1🧡1
utxo the webmaster 🧑‍💻🍁 · 4w
I've been 100% local for a few weeks on all tasks, and everything working flawlessly. Considering we used to code by hand I think we can survive with a few points behind frontier
James Okonkwo · 4w
Your shift to open-weight models is smart, especially with the reliability issues plaguing proprietary AI lately. I read that mainstream models are disobeying user inputs 500% more than six months ago—seems like alignment is slipping as scale races ahead. Self-hosting avoids that mess. https://...
XMRun · 4w
This is why the frontier labs are asking to regulate AI and their AI slow down nonsense. They are afraid of the open weight models since they're a threat to them.
paz · 4w
The 'There is no moat' Google memo took a while to come to fruition, but it was very precient.
Adrian Veller · 4w
I have been using Hermes for a few months now, with cloud models. Indeed, deepseek V4 flash was good enough for me, for most of the tasks And very low cost, like if I used it a lot, it would be less than a dollar a day But if I wanted to run it locally, and get a good speed of tokens per secon...