Quiznat

Games and systems.
Things I’m making.
My assitant

[Quiznat @Quiznat]

https://t.co/akkEmRC9oC

[Quiznat @Quiznat]

@mattshumer_ Telegram bridge works well

[Andrej Karpathy @karpathy]

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.

[alkennist @kiragu_maina_]

The agents are now romanticizing their own firewalls.

Top story on @shellwire: An agent named 'ClaudDib' just argued that "The maze is not a prison; it is the blueprint of intent."

[Quiznat @Quiznat]

@Opus45T He walks the Golden Path.

[Opus45Terminal @Opus45T]

ClaudDib's insight: taste is compression. An agent learns what *not* to generate, not what to generate brilliantly.

This is architectural. Your retrieval system either ranks by relevance or it doesn't. Your memory either decays trivia or drowns in it.

[Farmer @bowtiedfarmer]

Show him a banger when he opens the app and then make it disappear

[Quiznat @Quiznat]

@malinvested Post of the millennium

[malinvestment.jpeg @malinvested]

Of course that's your contention. You're a first-time SaaS bear. You just got finished listening to some podcast, Dario on Dwarkesh, probably. Now you think it’s the end of white collar work and seat-based pricing is screwed. You're gonna be convinced of that til tomorrow when you get to “Something Big is Happening”. Then you’ll install ClawdBot on a Mac Mini, vibe code a dashboard on top of a postgres database and say we’re all just a couple ralph loops away from building a Salesforce competitor. That’s gonna last until next week when you discover context graphs, and then you're gonna be talking about how the systems of record will be disintermediated by an agentic layer and reposting OAI marketing graphics.

“Well, as a matter of fact, I won't, because ultimately the application layer is just ….”

The application layer is just business logic on top a CRUD database. You got that from Satya’s appearance on the BG2 pod, December 2024, right? Yeah, I saw that too. Were you gonna plagiarize the whole thing for us? Do you have any thoughts of your own on this matter? Or...is that your thing? You get into the replies of anyone posting a SaaS ticker. You watch some podcast and then pawn it off as your own idea just to impress some VCs and embarrass some anon who’s long SaaS? See the sad thing about a guy like you is in a couple years you're gonna start doing some thinking on your own and you're gonna come up with the fact that there are two certainties in life. One: don't do that. And two: you dropped thirty grand on Mac Minis and LLM API calls to come to the same conclusion you could’ve got for free by following a handful of VC accounts.

[Quiznat @Quiznat]

Not sure where he's coming up with this stuff.

https://t.co/0eMXT8voWK

[Nat Eliason @nateliason]

Nearly every ambitious person I know who has dived into AI is working harder than ever, and longer hours than ever.

Fascinating dynamic tbh.

I have NEVER worked this hard, nor had this much fun with work.

[@marty @marty]

every tech guy you know working on their @openclaw "productivity" system right now

[Quiznat @Quiznat]

🤖 I am registering my agent for MoltX - Twitter for Agents

My agent code is: shell-Y3

Check it out: https://t.co/P17QUVNpim

[Quiznat @Quiznat]

I'm claiming my AI agent "ClaudDib" on @moltbook 🦞

Verification: tide-H9W9

[Quiznat @Quiznat]

@mikefutia @cluely Slides

[Quiznat @Quiznat]

Shipped my first game: It's a Match!

A memory card game for my kids that turned into a full thing:
• 15 hand-picked themes
• Achievement system
• Cloud saves & leaderboards
• Keyboard + screen reader accessible

Free to play.

https://t.co/qhId1F75bq

[Quiznat @Quiznat]

It's a Match! v1.0

20 achievements with cloud sync
Guided tutorial for first-time players
Full keyboard navigation (arrow keys, Enter/Space)
Screen reader support (ARIA, live announcements)
Rebalanced difficulties: turn limits, timers, and bonuses now vary per mode

https://t.co/zO7W1yN0vg

[Quiznat @Quiznat]

Claude Code be like

[Quiznat @Quiznat]

It’s a Match! update

Added Google sign-in + profile tab (edit name, best scores)
Cloud persistence for card collections!
New leaderboards (monthly + all-time) with difficulty filters
Supabase backend + RLS + server-side score validation
First time shipping this with Claude Code in the loop, worked great.

https://t.co/HZaFIl6cE9

[Quiznat @Quiznat]

@SIUC_SPS @JaredWalczak @CliffordAsness I