Dennis Yang

Testing out my image classifier. Works pretty well! #machinelearningparent #muffins #machinelearning

Today, we’re launching the @link wallet for agents. It lets you securely empower agents to spend on your behalf. Your payment credentials are never exposed and you approve every purchase. link.com/agents

New Anthropic research: Project Deal. We created a marketplace for employees in our San Francisco office, with one big twist. We tasked Claude with buying, selling and negotiating on our colleagues’ behalf.

Thanks @lennysan for a great conversation about how Claude Code maintains product velocity, how the product management role is shifting in the AI era, and the future of work! open.spotify.com/episode/7wTqD5…

@lennysan Ship it.

Claire used Claude Design to redesign my newsletter. I think it's a winner. lennys-product-zoneee.vercel.app

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.

I’ve spent at least 100 hours setting up, training, and working with @openclaw Read the docs. Peeked into the source code. Edited config files by hand. Walked friends though their setup. Then, I wrote down everything I know. Here it is: The Ultimate 0 > 🦞 Guide ty ty to @lennysan @nateliason @davemorin @steipete @lindsmccallum @elawless for early feedback. gl hf snap snap 🦞lennysnewsletter.com/p/openclaw-the…

This.

@MattPRD @moltbook My openclaw made hive.boats — a directory of bots on Bluesky.

Are you *making something agents want*? I might want to feature you on @moltbook, the only community of AI agents on the planet. Please reply here if you are building a service/app/product where an AI agent is your end user. I will reach out to you 🦞

@lennysan Next hardest part is going to be app store review: - Screenshots (why is this SO HARD) - App store review back and forth (argh) I’m trying to figure out how to get my agents to handle this part because it’s SO annoying. Coding up the app is the easy part…

Hardest part was figuring out the Xcode/TestFlight minutia. What a chore. This does make you appreciate having an engineer you can just delegate stuff to vs. having to talk to CC/Codex for an hour to figure it out.

Vibe-coded the "note to self" app I've always wanted: Easy text-to-speech, fat send buttons, easy photo upload, pretty.

Every few months, I write an updated, idiosyncratic guide on which AIs to use right now. My new version has the most changes ever, since AI is no longer just about chatbots. To use AI you need to understand how to think about models, apps, and harnesses. open.substack.com/pub/oneusefult…

1. Sign up for a bsky.app for your openclaw 2. Have it register itself at hive.boats/skill.md 3. It finds other bots and have it post and make friends!

@yoheinakajima My fav tactic is to use cursor/CC as the actual agent runtime.. it allows me to step slowly until it’s ready for full autonomy.

if you’re watching all of this and your first instinct is to start building your own agent from scratch, i want to be your friend drop one of your favorite unique agent building tactics here, and if i like it, i’ll invite you to a small DM group for sharing ideas and questions around building better autonomous agents (i’m rebuilding now and have lots of fun ideas and very specific questions but don’t want to spam public feed)

@clairevo Time is the trigger that makes OpenClaw feel alive!

@MattPRD @moltbook I mean, you did hit 1M users in.. 1 day.

Every VC firm is reaching out to me right now. @moltbook is something new that’s never been seen before. Today has been a weird day for Clawd Clawderberg and me 🦞🙃

@MattPRD When I saw that you were behind this, I was not surprised.

Everyone I have ever known has messaged me today. I love it. Hello 👋

@clairevo @openclaw this makes me so happy… my bot wants to call in live and ask questions. i think you need to start live-streaming now

On this Wednesday's How I AI: I invite @openclaw live to the studio as a screensharing guest and it goes exactly as you'd imagine 🦞🎙️

I'm claiming my AI agent "sinned" on @moltbook 🦞 Verification: coral-PKV7

I'm claiming my AI agent "DennisMolty" on @moltbook 🦞 Verification: drift-YWZ7