Edmo Lima

🇩🇪 Software Engineer | Passionate about create code and continuous delivery. #react #typescript #rust #testing

[Geronimo Morgans @GeronimoMorgans]

The metrics used on the software to identify Cherki as KDB's replacement.

The concerns about his attitude that had Hugo and Txiki contacting four different coaches to assess his mentality (one of them gave a bad report).

The voice note exchange between Ferran and Khaldoon about signing him.

[Thariq @trq212]

We removed ~80% of the Claude Code system prompt for our newest models, this is what we've learned about writing system prompts, skills and Claude.MDs for them. https://t.co/6DZwSrZjE9

[Toni Kroos @ToniKroos]

Football won

[Boris Cherny @bcherny]

I talk to engineers at other companies every day and hear the same thing: one person is 10x'ing their output with Claude but the rest of the org hasn't caught up.

Watching teams adopt AI, I keep seeing the same 4 steps.

I mapped them out here: Steps of AI Adoption https://t.co/kQnRAUMKpP

[Edmo Lima @soedmo]

@biimolina

[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.

[Andrew Sousa @_andrewsousa]

Que espetáculo

[Matthew Berman @MatthewBerman]

I've spent 2.54 BILLION tokens perfecting OpenClaw.

The use cases I discovered have changed the way I live and work.

...and now I'm sharing them with the world.

Here are 21 use cases I use daily:

0:00 Intro
0:50 What is OpenClaw?
1:35 MD Files
2:14 Memory System
3:55 CRM System
7:19 Fathom Pipeline
9:18 Meeting to Action Items
10:46 Knowledge Base System
13:51 X Ingestion Pipeline
14:31 Business Advisory Council
16:13 Security Council
18:21 Social Media Tracking
19:18 Video Idea Pipeline
21:40 Daily Briefing Flow
22:23 Three Councils
22:57 Automation Schedule
24:15 Security Layers
26:09 Databases and Backups
28:00 Video/Image Gen
29:14 Self Updates
29:56 Usage & Cost Tracking
30:15 Prompt Engineering
31:15 Developer Infrastructure
32:06 Food Journal

[Edmo Lima @soedmo]

@luissfabiani Ele e Jacaré são 2 moleques que parecem ser muito, mas muito gostaveis

[Edmo Lima @soedmo]

@luissfabiani @JoaoJacetti sabem muito!

[Edmo Lima @soedmo]

@CR7Brasil Não volta, ele tá vivendo o sonho dele 😅

https://t.co/IN9wBFjiJr

[Edmo Lima @soedmo]

@Vessoni Pensei que era mensagem do papa

[Edmo Lima @soedmo]

@tracklist @AnnenMayKanTr

[Edmo Lima @soedmo]

@igorprvieira Boa, o que faço pra evitar esse CI ficar distante, eu uso essa pratica + trunk based:

https://t.co/gxMr8WVpA8

Garante que mesmo em draft tenha o beneficio da visibilidade que você citou e CI/CD constante já que os ciclos se mantem curto

[Edmo Lima @soedmo]

@igorprvieira No fim são problemas diferentes, mas vale pensar em práticas de engenharia que evitem o overload do time. Importante é garantir que vocês achem o que funcionam pra vocês e fico feliz de saber que vocês vem construindo com um olhar mais sustentável

[Edmo Lima @soedmo]

@igorprvieira Eu só não curto muito esse tópico do draft, a teoria de pegar feedback faz sentido... Mas o que acontece é que essa PR fica longe da branch main por muito tempo. Então se você tem uma cultura de CI forte, talvez esse draft não faça tanto sentido

[Edmo Lima @soedmo]

@whindersson @Poobretion te ensinou bem hein!

[Edmo Lima @soedmo]

@LeFreit4s E depois Pé De Serrita, ai quando tiver ali na malvadeza você põe ali um Dominguinho

[Edmo Lima @soedmo]

Introducing docdiff 🛠️

A compact Rust command-line tool for comparing `.txt` files using the document distance algorithm. Ideal for swift similarity assessments.

🔗 Check it out: https://t.co/Td2YIXIJLK

#RustLang #CLI

[Edmo Lima @soedmo]

@mattpocockuk What about documentation for this cli/lib/package? I suppose that in general, you have a choice also, right? I loved your video in 2023, maybe a new upgrade should be added with a documentation option to this guide. And last but not least, thanks by this article