taude

That's pretty neat. Was fun seeing Seattle rendered this way

Our skills and agents use deterministic tools for things like: linting, ayy1, etc....

We have the exact same thing, we actually install a "plugin" engineering/org wide, and one of the skills in there, is a /skill-mananger skill that can browse other skills in another repo, install, uninstall, and create new ones with all our specific requirments. Semantic versioning allows us to have a hook to auto apply updates, too.

Seems to be helping people share things around the org.

This is pretty much what I've been saying for 20 years, but with content in general. People's time is fixed: 168 hours per week to: work, sleep, eat, excercise, commute, and then....

- read

- watch content: a movie at a theater, youtube, short-form socials, streaming services, etc..

- read a book

- scroll on the phone (won't list all the apps out)

- play a video game

- play a board game

- listen to music

etc.

So much content, fixed amount of time.

Funny, Nix is next on my list.

I'm setting up my new blog right now. I'm thinkin of having a toggle to "hide" ai generated content from my main list of writing, and labeling (and a disclaimer at the toop of each ai-generated post a message).

Example home page: https://taude.xyz/ Example AI Slop post: https://taude.xyz/posts/the-tool-stack-behind-this-blog/

Not trying to self-promote, but honsetly trying to leverage AI when appropriate, and to also not take away from my hand-written articles that are typically my thoughts and opinions....

- I get OS level notifications when the agent is ready.

- I don't need to use TMUX's wonky keyboard shortcuts

- I moved off of TMUX anyway, when ssh-ing into remote servers became 'not a thing'

- automatic coding session management, like auto resume, layout manamgement, etc. out of the box, without setting up TMUX, which could be a wormhole for some, by the time you fix mouse scrolling, cut/paste, etc...

I'm currently using CMUX, and been pretty happy with it it at this time, but loving the evolution of all these tools

they're refering to this: https://futurism.com/artificial-intelligence/ai-companies-de...

just like ai will create amazing tests suits for the broken code it writes, if one isn't carefully watching...

EDIT: of course it probably helps to have an up front tdd test suite, but often isn't the case.

Funny enough. I never smoked, but I often went and hung out in smoking sections outside our work office. I really enjoyed how open smokers were to just random conversations, and the quick 10 minutes of not looking at the screen were typically energizing. Almost like a natural pomodoro work schedule that forced up out of our desks, and then out of our offices.

When i was in college, we wrote a lot of C code in those blue notebooks. And this is a long time ago in a galaxy far, far away, which is probably why I don't totally didn't hate whiteboard coding tests. And when I'm trying to work with a new programming language or tool, I'm usually writing things out by hand (helps with the memory, like the article referenced).

i've actually had marketed to me on the socials a course on "transcribing" professional writers demonstrating various angles of the craft. I'm sure the course was vibed or something. Pretty easy to identify authors you like, and whose dialog snaps, whose descriptions you identify with, whose doing great character development, etc. And then transcribe them....

EDIT: maybe the term I was looking for is: copywork?

Also, Google isn't scraping your data....

The Tour De France had one a long time ago, writing chalk signage on the roads [1]. I had to search for the YouTube video about it....

[1] https://www.youtube.com/watch?v=Khffa2GkvPE

If i'm reading this correctly, can run Immich from a Raspberry Pi 4? That's pretty cool.

I bought all the stuff (new case, networking card and a Jonsbro N4 to repurpose some intel i7-9700 era processor and motherboard, but didn't get it setup yet, as I was starting to rethink the power consumption....

Also looking to use this rebuild as an opportunity to learn Nix.

Let me know if you all have some good article references, to point me at. I've been doing some research, but could always do more.

I may end up putting a low power NUC in the case, or something. I don't know...

I remember collecting original Shatter when it came out. The big novelty was that it was 100% created on a computer. Pixels and all in the output.

it said in the original article on the bun rewrite ~165K.

Everyone is deluding themselves if they think their enterprise privacy contracts with these frontier model companies (especially in CA) aren't reading and processing their private data

I do a really lightweight version of flash cards. Everytime I'm learning a new tool or tech, I grab oversized notecards (my favorite are 8x5" dot-grid cards). I put a label at the top, and create bullet points of each item i want to remember. I then review. No individual cards for each item or anything. Just all the things grouped on one card as bullet points.

For example, I'll have a `sqlite` card, and put all the commands and everything on it, as I learn them. I'll use it as a cheatsheet, but then also a few minutes of mindful review. This for the toolings that I want to know well enough to not get slowed down googling the commands. I do this for a lot of CLI tools, but also things I need to remember about the business of my company and working across group, etc....

Eventually the five or six working cards I have, get put on a pile and new ones come in.....

at least you haven't optimized a workflow to convert the page to markdown file, download locally into some folder that you watched 30 youtube videos on how to organize your knowledge graph....to never read later, or to burn 10s of Ks of tokens to build into karpathy wiki knowledge tree....

This is what I'm hoping to do. I haven't done much research yet, so I look forward to reading about your learnings. (Also to the person who responded to you with their experience and link.)

Thanks for saving me probably some hours...

EDIT: I'm also coming from an old Synology NAS from the ~2015 era.

I shift a 1 GB electron app to a 900 MB browser tab (i don't know what it actually is, but the number of Tabs I have taking up 1 GB memory is shocking these days).

Trying to vibe as many of my own CLI toolings as possible....

My favorite google hallucination was that the famous jazz bass player, Jaco Pastorious, who passed away in the mid-80s, was the bassist for Metallica. I have a screen shot of that one around....

Not real work. It's an amazing couch laptop, though. I do have a full CLI tooling pipeline setup, though. I mostly read, research, and write on it. Chrome tabs galore open, Obsidian, etc...

It's pretty amazing at the price point. Thought last year the M4 Airs were on sale for $749 -- I'm doubtful we'll see that price again on those....

I'm on a NEO right now, my Chrome has like 25 tabs open. Doom Emacs running in terminal, Obsidian open, Apple Music, Apple NOtes, etc. I have a lot open...

AND I'm not seeing this issue. What am I missing?

I'm on 26.4.

:shrugs:

EDIT: I guess I wait to update and install the latest version? Maybe the linked page could have stated there's a new regression in newer MacOS versions that introduced this?

I don't think frontier model providers are going to be incentivized to invest in this much, yet. Once inference gets more competitive, sure. I haven't looked lately, but won't be surprised if tools like OpenCode do do what you're suggesting, though. Third-party coding harnesses ARE aligned to deliver this type of feature and optimization.

Thanks. I've added

Did everyone like this Stephensen in this thread? I read Cryptonomicon and Seveneves, mostly. They slogged for me a bit. But I love what he writes about, so willing to try another one (even if he doesn't have an editor). It sounds like this could be topical 2027 read. I have a long summer ahead of me.

I need the equivalent of Claude Code, but for hardware projects, so I can actually do all the projects I envision with the EPS32s.

Something that combines: 3d printing; auto procurement of parts; custom software writing; maybe a robot arms or something, all in a nice box on my desk that I feed parts into like a mail slot. PROFIT.

Ha, if I had $10M, i'd be way gone. Pretty sure I could live my lifestyle for the next 30 years on that. I could live it on $5M, pretty easily. But where I'm at, I'm at the fringe, even if I have to move to Canada for healthcare when I'm old. And I'm saying this from having a house paid-off (where the taxes went up something like 40% last year -- and I'm guessing will keep going up?).

I'm not convinced living in the US that all the financial planning algs that big finance institutions are using and going to hold up in the future, and curious how it works for a whole generation. But time will tell. So far the cycle always corrects itself. I'm especially curious how it works when there's going to be a lot more early to mid-50s employees being forced into retirement, who are going to be living a long time, yet.

I'm especially paranoid about my prospects of retirement if the market dives 50%. It's happened in the past, and plenty of old hacker news articles about how it really screwed up people's retirement plans. Look back at Stock market returns for some tech companies from 2000 - 2014. That's a big span to fill.... ( I think I read somewhere that the market return for 2000 - 2010 was just over 1% year, someone should fact check that, though).