
Chris Chambless will never comply
3.7K posts

Chris Chambless will never comply
@Lumenbeing
coincidence theorist debunker, fact checker checker
California, USA Beigetreten Mayıs 2008
294 Folgt187 Follower
Angehefteter Tweet

D&D has always had too many ability scores. And the current edition has too many saves. Here’s what I think makes sense.
3 ability scores and 3 saves
Abilities
💪 Might – strength + toughness (no more Con)
🏃 Agility – more appropriate than Dex
🎭 Presence – force of personality and will
Saves
Fortitude - vs toxins, mortal wounds and environmental
Reflex - dodge physical dangers
Resolve – resist fear, madness, charm
English

@LLMJunky the unified experience across devices is honestly what sold me on it
being able to start something on desktop and pick it up on mobile without any friction is such an underrated feature
English

The Codex app server was such a brilliant stroke of foresight that really doesn't get enough love
Not only are you allowed to use your chatgpt account with any harness, but you can build your own apps directly on top of theirs.
They just make building on and with codex such a great experience
To demonstrate this utility, I want to highlight the kitty litter app, made by @SIGKITTEN.
Instead of having to build the entire harness, and all the infrastructure, he's plugged into the app server for a unified experience between mobile and dev machine.
When I create a session on my computer, it's automatically available on my phone. All of the chats you see in this video automatically populated when we connected to the app server.
All my skills. My agents. My sessions. My folders. My prompts. They're all ready to use - automatically.
Because they're exposed by the app server, along with many other endpoints.
It's a great ux/dx that really deserves some love.
It's almost like they want you to build on top of their products ;)
Btw Litter is great 👍
English

@Lumenbeing @lexfridman @karpathy Yes - but his uses voice mode to converse with it - not passively listen to it.
English

LLM Knowledge Bases
Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:
Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.
IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).
Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.
Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.
Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.
Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries.
Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.
TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.
English

@lexfridman @karpathy Isn’t that what Notebook LM does?
English

Same, I have a similar setup. A mix of Obsidian, Cursor (for md), and vibe-coded web terminals as front-end.
Since I do a podcast, the number/diversity of research interests is very large. But the knowledge-base approach has been working great.
For answers, I often have it generate dynamic html (with js) that allows me to sort/filter data and to tinker with visualizations interactively.
Another useful thing is I have the system generate a temporary focused mini-knowledge-base for a particular topic that I then load into an LLM for voice-mode interaction on a long 7-10 mile run. So it becomes an interactive podcast while I run, where I ask it questions and listen to the answers to learn more.
Anyway, heading out for a run now, thanks for the write-up 👊
English

@CorpseKings I almost beat He-Man today…Damn you He-Man!
English

@naiivememe This actually happened to me at age 20
English

@RaineyOvalle Neither. That book sucked. Nevwr reading it again no matter which cover it has
English

Exactly.
And the de-swagification of book covers needs to be studied.
Tell me which one of these you’re more likely to read.


go hang a salami, im a lasagna hog@MattGrippi
@RaineyOvalle i judge books by their cover constantly and it often pays off
English

@BRICSinfo The upgraded version got 5 stars on Anazon
English

@jakeshieldsajj You got hit in the head a few too many times.
English

The UK is basically one big terror cell at this point. They let the enemy through the gates and they are being held hostage
Keir Starmer@Keir_Starmer
I will always make decisions in the national interest. That’s why we did not join the offensive action against Iran. Reform and the Tories would’ve rushed us into war without a plan to get us out.
English

@NiohBerg We had to first sideline Russia by getting them out over their skies in a protracted war with Ukraine
English

@TrumpDailyPosts The entire ariticle attributed to Todd was written by AI
English


@Ilegvm We were called Generation Y or “why” for a hot minute.
English

Why is Canada so retarded?
Tablesalt 🇨🇦🇺🇸@Tablesalt13
🚨NEW - CANADIAN SCHOOL DESIGNATES CAFETERIA AND LUNCHROOM AS "NO FOOD ZONES" FOR RAMADAN Fairview school in Calgary Alberta has implemented bans all food from its cafeteria and lunchroom for Ramadan the children who are NOT fasting have to find a spot to hideaway and eat!
English

@GHHILL1911 @ViktorGorchev Oh okay. Reading “investors” confused me. I was wondering how anyone still had a claim on a ship’s cargo that was lost over a hundred years prior.
English

Imagine you had to choose your life at age 40:
Option A:
Single. No kids.
$10M net worth.
Travel anywhere. Total freedom.
Quiet house. Quiet holidays.
Option B:
Married. 3 kids.
$1M net worth.
Drive a Toyota. Chaos every morning.
Loud house. Full dinner table.
Be honest, which life are you choosing?
English

@ksorbs Because of gerrymandering like prop 50 in California
English

Why is the right seemingly losing so much support?
Polymarket@Polymarket
BREAKING: Democrats now projected to seize control of both chambers of Congress this November.
English

















