Monbiking

[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.

[Leonard Rodman @RodmanAi]

The creator of Claude Code just broke coding in 30 minutes.

No long tutorials.
No fluff.
Just pure “vibe-coding.”

People spend HOURS learning this… and still miss it.

Save this.
This changes how you build forever.

[Monbiking @Monbiking]

@aena Barcelona T2. Los agentes nos comentaron al pasar que no ‘había gente’ y los puestos automáticos estaban apagados

[Monbiking @Monbiking]

El caos continúa. Que manden a más agentes de aduana! @aena @aeroinfo @AeroinfoBCN

[Monbiking @Monbiking]

@AeroinfoBCN caos in T2.
Dos únicos agentes de aduana para una fila inmensa de pasajeros

[Monbiking @Monbiking]

@jspujji LinkedIn

[Monbiking @Monbiking]

@juann_ayuso @MarcHirschi Piano piano…

[Monbiking @Monbiking]

@juann_ayuso @tds @TeamEmiratesUAE Monster!!! Super pace!!

[Monbiking @Monbiking]

@juann_ayuso Vamos capo!!!

[Geraint Thomas @GeraintThomas86]

Much happen at the Tour today? 🤣 Few 30/30s on the bottom of Galibier. All good training for the Commies 🤣 Big 10 days to go 👌💪 #TDF2022

[Monbiking @Monbiking]

@madedotcom Order no: 10388436 Another month of delay on top of the standard three months of waiting?!?! I understand the logistics constrains due to pandemic and Brexit etc, but if you commit to a date, pls deliver. All I got was ‘ops, we’re sorry’, come on!! #customerservice

[Carlton Kirby @carltonkirby]

Federico Bahamontes, here on the left, was the King of Kings of the Mountains... I missed his birthday this summer. The Eagle of Toledo turned 92. That's Anquetil with him here... He wasn't too bad either. I think this is 1964

[Orla Chennaoui @SportsOrla]

While temporary bike lanes are removed, and LTNs disputed, Amsterdam city council have made Harlemmerdijk, one of the busy roads in the city centre, open only to bikes and pedestrians.

[The Quote @thequote]

Celebrate your success and find humor in your failures. Don't take yourself so seriously. Loosen up and everyone around you will loosen up. Have fun and always show enthusiasm. When all else fails, put on a costume and sing a silly song. - Sam Walton

[Carlton Kirby @carltonkirby]

The recent "Bring Your Pet To Work" initiative has clearly gone too far. That said, Bauke's duck chick did enjoy the chat with Tom apparently

[Netcompany INEOS @NetcompanyINEOS]

Today at the Tour we start in Pau, Nico’s home for many years.

This is how we will always remember him ❤️

[Netcompany INEOS @NetcompanyINEOS]

3 Grand Tours
3 Leaders
1 Common Purpose

Sir Dave Brailsford expands on our racing plans for 2020

[Laura Meseguer @Laura_Meseguer]

.@ivan_cortina ficha por @Movistar_Team para las próximas tres temporadas. El equipo español continua apostando por el talento nacional ⭐️⭐️⭐️⭐️⭐️
📷 Photo Gómez Sport

[Positively Positive @PosPositive]

There are people, things, and moments worth cherishing forever. Then, there are those it’s better to let go of, leave, resign — and never look back. https://t.co/Ca66bgRXfP by @wing_flutter

[The Quote @thequote]

Do you want to know who you are? Don’t ask, act! Action will delineate and define you. - Thomas Jefferson