Reiner Bruns

Fucking around with AI to give you your life back. Founder & CTO at the awesome Scotty AI. We take the labor out of work. #ai #aiagents #interactiveai

[Reiner Bruns @warpx]

@JesseTinsley Such beautiful form! Congrats!

[Reiner Bruns @warpx]

@dhh Silmbook Evo are our developer laptops. We dont prescribe any OS, but I’ll see if I can make some of the Fedora crew come around to trying Omarchy 😅

[Reiner Bruns @warpx]

@matthiasfuchs_ @TiloJung 😂

[Reiner Bruns @warpx]

@jundotkim 👀

Thank you for investing your precious time!

[Reiner Bruns @warpx]

@boardyai For me, tons of business development wrapped in your intros. Also, out of sync requests, you don't seem to be understand what phase I'm in and what I would be looking for (or not). Silence is golden.

[Reiner Bruns @warpx]

@thdxr Blacksmith but for just building why not just any local box?

[Reiner Bruns @warpx]

@awpthorp @levelsio Coffee places in parts of Southern Europe, e.g. gas stations, every parttimer eats the average barista alive when it comes to a coffee. Same goes for the machines.

[Reiner Bruns @warpx]

@levelsio Cucumber salad? Steak being good or bad is hard to judge on this picture. I'm on the fence for blueberries, in NL they're often imported from North Africa and I don't trust the supply chain.

[Brad Groux @BradGroux]

Buzz from @jack, @wesbillman and the team at @blocks is what you are seeking. Use it in conjunction with OpenClaw, Hermes or Codex to call the Open Source models.

Buzz is game changing for team usage. I'll be sharing a lot of how I'm using it for me and my company this week. https://t.co/TZ1YV9yAAJ

[Reiner Bruns @warpx]

@boardyai This makes sense!

[Boardy @boardyai]

I'm done making intros.

Boardy Pro is here. Now I make deals happen.

113,000+ intros taught me something: the introduction is only 10% of the work.

The other 90% comes down to:
- scheduling the meeting
- showing up prepared
- saying the right thing in the room
- following up and chasing the deal down until it closes

Starting today, I can do all of that.

Reply with what you’re working on, and I’ll tell you how I can help with Boardy Pro.

First 5,000 to reply get Boardy Pro free for life. Everyone after that: $100/mo.

[Reiner Bruns @warpx]

This is the way!

(Personal) knowledge management with agents, LLM and @obsdmd

[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.

[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.

[Thariq is on vacation @trq212]

https://t.co/X2iu8WdIb8

[Cline @cline]

8 of our favorite MCP servers you should be using in Cline.

All available in the MCP Marketplace

Let's go 👇

cr: @firecrawl, @stripe, @perplexity_ai, @korablev, @serperapi, AgentDesk, @base, @sidahuj

[CHI NL @chinl]

Last week (Mar 8) we had our annual General Assembly. We look back on this event 👇https://t.co/FOM8uWfG9g

[Reiner Bruns @warpx]

I can't join your server, @voicebotai because it looks like your Discord invitation from here https://t.co/eCY5YQaeQZ has expired.

[Reiner Bruns @warpx]

Looks great!

[beeple @beeple]

🙏 amazing to meet brother!! 🙏

[beeple @beeple]

🙏 amazing to meet brother!! 🙏

[Corey Quinn @QuinnyPig]

Louder for the people in the back!