No output to this prompt, not even an error: AI, opps nope SI is huuge. The best evar.We're gonna be rich right?
Needs a huggingface gguf
564 karma · joined March 1, 2012
No output to this prompt, not even an error: AI, opps nope SI is huuge. The best evar.We're gonna be rich right?
Needs a huggingface gguf
llama serve -hf unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_XL
but it failed my basic prompt to compose a vim regex to match CamelCaseWords
downgraded a bit with Q4_K_M from ollama run qwen3.8:27b
and /set nothink and at least 1 regex matched FooBar
prompt eval at 2.8 t/s eval at 0.94t/s
I particularly enjoyed this usage of the regex: /%\1\%/ ... onward for 700+ characters of \%\/ :-)
[1] Lion Kimbro. How to Make a Complete Map of Every Thought You Think. 2003 https://users.speakeasy.net/~lion/nb/book.pdf
It's like an analog computer of weaving.
If you have any experience with weaving you will understand the importance of shed formation. The key innovation is the heddle mechanism which affords great efficiency with weft pattern making through rotation of a pattern bar allowing the weaver to focus on other variables like yarn selection or design sequence. There is even a web app pattern picker to plan out designs developed with the help of a mathematician [1]
Perhaps other similar ideas might be something like tablet weaving [2] or Der Weberknecht [3]
The primary difference is the quick prep and setup time with the boom loom and it's near instant to develop modular samplers [4]
If anyone knows of any other hacking mechanical weaving machines like the boom loom; please share!
[1] https://www.theboomloom.com/krokbragd-picker
[2] https://en.wikipedia.org/wiki/Tablet_weaving
[3] https://weberknecht.notion.site/Projekt-Weberknecht-Project-...
but I find it curious that the many will always pay for the few https://youtu.be/y12yZ7bQizk?si=Mbgg-F7IP8HJXJPz
and at what cost ? https://youtu.be/-sNKfRq1oKg?si=6m8pVM9tvawohUbm
Why not just mechanical turk the codebase? Lotsa jobs even with LLM augmentation at current state.
Where is the long term thinking of utility vs cost?
Until AI can solve its own energy generation issues, the hype is gross.
Thankfully I'll be long dead (hopefully) before a local AQI > 500 is considered the new normal common good trade for high fidelity personalized deep fake pr0n
or the cure for cancer at US healthcare billable rates.
I hope this trend is not industry wide. A publisher chasing fads and trends over enduring quality, so sad. I wish I knew who the publisher was to avoid but I can foresee their pivot to AI authors with titles like "From Zero to Hero, ChatGPT 5.2 Top Prompting Secrets for Dummies"
I practice this in my day job, as in that is the default mode for continued employment. Not sure how these practices are new. I wonder if it is a generational thing.
Yes, arms instead of fingers, thanks for the great ergonomic video link, this was the most surprising finding when I got into fountain pens and feels like a totally different skill from the school days of handwriting cursive: https://www.fountainpennetwork.com/forum/topic/372976-recomm...
[{ "title": "HyperClay", "text": "2025-08-18 Experience the Zen of making, hosting, and sharing great software in a single, portable, self-updating, vanilla HTML file\nBuild web apps like you're sculpting clay, not managing infrastructure.\n\nModern web development forces you through layers of abstraction: config files, build steps, magic frameworks, deployment pipelines.\n\nHyperclay returns to a simpler model: your app is a single HTML file you (and your clients) manipulate directly. Edit the file through its visual UI and it persists its own state.\n\nWhat if web apps were as simple to edit as documents? Hyperclay makes it possible: UI, logic, and data live in one self-modifying HTML file. Edit it live. Share it instantly. Download and use it locally.\n\n---via [[Single-file HTML apps | Hyperclay|https://hyperclay.com/]]", "tags": "SelfHost Html TiddlyWiki Spa NodeJs", "type": "text/vnd.tiddlywiki", "created": "20250818000000000", "modified": "20250818000000000" }]
Pretty easy to get started after signing up at login.gov
then https://www.archives.gov/citizen-archivist/get-started-trans... with video: https://www.youtube.com/watch?v=dwQ5pEWWFY8
The support forum is https://historyhub.history.gov/citizen_archivists/ to ask questions
MX doctor
enter prompt, type RET twice to submit
pass output to https://github.com/rupertl/eliza-ctss or modern llms