Tara Tiger Brown, PhD

@beeple very cool. next visit Canada. :)

GM!! will be speaking at Stanford at 5pm today!! come say hi!! 🫡🥰❤️🦾

@trishprattle @seanbonner Trish!

@tara @seanbonner Tara!

One doesn’t need an in depth knowledge of Catholic theology to recognize that The Pope probably has a more authoritative position and deeper understanding of it than Trump (or Vance for that matter).

@seanbonner @karpathy @mccoyspace I am so happy you made this. I was managing the wiki and book library separately.

I combined @karpathy's LLM-Wiki and @mccoyspace's LLMbrary into a single knowledge base for your archival references (books) and current research (notes, web clippings), and helps you find the synthesis and synergies between them. 1/2

@Av1dlive @eng_khairallah1 The older video is helpful. Anthropic's Prompt Engineering Tutorial is an up‑to‑date reference for Claude’s latest models, including things like structured outputs, tool use, and agentic patterns that don’t show up in that video. platform.claude.com/docs/en/build-…

This 24-minute prompting workshop by Anthropic's own applied AI team will teach you more about getting real results from Claude than the last year you spent guessing at prompts. Watch this, no matter what. Then read the 25 prompts below by @eng_khairallah1 that save you 15 hours every week.

I know it's kind of patting myself (or Claude anyway) on the back, but my daily Quicky emails are getting really solid. Check out todays: quicky.email/digest/seanbon…

I recently moved a bunch of my older (and still available photography) NFTs from @foundation over to @opensea and thought it might be a good time to revisit some of these collections for anyone who might have missed them. Might as well start off with this classic:

My blog post turned short book on Changing the Conversation Around AI & Art continues this week. Before the next part is published feel free to catch up on the earlier installments. Links below:

I love email newsletters and in an ideal world I’d read every one that I subscribe to every day. But the reality is I rarely get to do that and they just pile up unread in my inbox. I made Quicky to help manage that. If you relate, keep reading the🧵

@SumoHug @JJEnglert @openclaw Try YouTube - there are creators that will walk you through understanding at a high level then setup etc.

@JJEnglert @openclaw Is there a resource you can point me to in layman’s term for someone completely new but loves learning to take the first steps into doing this? Even after reading all this it’s so foreign to me

After a month of watching my fellow builders set up their @openclaw , I finally took the plunge this past week. Last night my agent ran overnight on a project we came up with together, and it was ready for review when I woke up this morning. It has its own GitHub account. Its own email. Its own Twitter. It runs 24/7 on an old MacBook Pro with the lid closed. And it has enough tools connected to actually do real work. But the magic moment wasn't the overnight build. It was something way simpler. I told it to message me at 7:30 AM with a daily plan. And it just did it. Figured out how to do it on its own. That "figure it out" mentality from an agent that actually has access to tools and a computer felt different than anything I've used before. For the first time, it felt like something capable of doing real stuff. Not a chatbot. Something else. And I'm just scratching the surface. It took me about 8 hours to get here. I want to help you get there faster. Here's everything I learned along the way, plus a prompt you can copy and paste into your OpenClaw once you're set up. Getting started I set it up on an old MacBook Pro. Dedicated device. You want this running independently so it does not have access to your data. Having a virtual device on @Hetzner_Online is also good. Installation took about an hour. Then I spent the next two hours having Codex tighten the security before training it anymore. Sandbox commands. Whitelist only what you need. Do this first. Then I hit a wall. It felt like a chatbot. Limited permissions. Couldn't access tools. Couldn't browse. It took another 2-4 hours to get terminal access and Playwright browser control working. I used Caffeinate in terminal to keep it running with the lid closed. I set up dedicated accounts. GitHub, email, Twitter. Give it its own identity so it can operate independently. Training it - Keep your Heartbeat.md lean. It gets read every session and burns tokens if it's bloated. Identity, active projects, key preferences. That's the hot cache. - Install a memory plugin early (ClawVault, Supermemory, or Lumen Notes). Persistent memory across sessions is what takes it from chatbot to something that knows your work. - Build skill files for recurring output. Emails, social posts, documents. Each gets its own file with format, voice rules, examples, and a checklist. It follows these like playbooks. - Define your agent's persona and tone. I built out voice files based on what I'd already created in Cowork and the output quality jumped immediately. - Point it at your existing repos. It can pull context from anything you give it access to. If you've already built structure somewhere, don't rebuild it. Reference it. Best advice I got from experienced OpenClaw builders Force plan before execution. Make it tell you what it's going to do before it does it. Saved me from multiple rabbit holes. Back up your repo to GitHub every night. Your config files, skills, and memory directory are the training. Lose them and you're starting over. Think in workflows, not one-off tasks. This compounds fast. I also applied the same repo structure from my Cowork setup guide: Your-Workspace/ ├── Heartbeat.md ├── Brain/ │ ├── about-me.md │ ├── brand-voice.md │ └── working-preferences.md ├── Skills/ ├── Projects/ └── Memory/ I'm about a week in. Still early. But I can see where this is going and I wish I'd started sooner. If you're just getting started, here's the prompt I'd paste in on day one to fast-track the whole setup: -- You are going to help me set up my workspace so that every future session starts with full context about who I am, what I do, and how I work. We're building the files and structure that make you useful from the first message. Interview me in phases. Ask questions, then build files based on my answers. Don't rush. Don't assume. Ask before you build. Phase 0: Foundation Check if I have a Heartbeat.md file. If not, create one. Keep it lean. Recommend a memory plugin for persistent context. Ask what tools I use daily and help me connect them. Recommend sandboxing and whitelisting commands from the start. Phase 1: Identity Interview me to create Brain/about-me.md. Ask about my work, background, what I'm building, and positioning. Show the file. Get approval before moving on. Phase 2: Voice Interview me about how I want my agent to sound. Phrases I use. Phrases I'd never use. Tone shifts by context. Create Brain/brand-voice.md. Get approval. Phase 3: Working Preferences What I want help with. Communication style. Workflow pain points. Output preferences. Create Brain/working-preferences.md. Get approval. Phase 4: Skill Files For each type of recurring output, create a skill file in its own folder under Skills/. Each gets: format, voice rules, examples, quality checklist. Ask what I create most often before building. Phase 5: Active Projects Current projects, goals, deadlines. Individual files in Projects/. Phase 6: Memory System Update Heartbeat.md with a summary of everything we built. Create Memory/ directory with subfolders for people, projects, context. Add glossary.md. Phase 7: Reference Sources Any existing repos, docs, or files I want referenced. Organize access. Rules: One phase at a time. Show each file before saving. If unsure, ask. Concise files. Lowercase, hyphens, .md format. Start with Phase 0.

@JJEnglert @openclaw Instead of caffeinate, consider pmset disablesleep. It changes the power profile once and survives reboots

@hTrapVader @sam_kirschner @villageglobal @seanbonner speaks highly of you

Chatting the evolution of coding agents with @sam_kirschner of @villageglobal Tap in to get a feel for where my head's at, and where I think things go next!!!

@witcheer Exactly. ChatGPT’s projects are just folders.

@dr_cintas I wish I saw this yesterday. I spent an entire day testing models…

Repo: github.com/AlexsJones/llm…

🚨 The #1 problem with local AI is now solved. There’s a new tool called llmfit that checks your hardware and tells you which models will run well before you download anything. So instead of guessing and hitting out-of-memory errors…it gives you a ranked list based on your machine. What it does (in one command): → scans your setup (RAM / CPU / GPU / VRAM) → evaluates models for quality, speed, fit, and context → selects the best quantization automatically → labels what’s ideal vs okay vs borderline The part I like most: it handles MoE models correctly. Example: Mixtral 8x7B has ~46.7B total params, but only ~12.9B are active per token, and llmfit accounts for that (a lot of tools still don’t). 100% Opensource.

@togethercompute When using moonshotai/Kimi-K2.5 does any request data ever go to Moonshot AI’s own infrastructure or Chinese‑jurisdiction servers, or is inference run 100% on Together‑controlled GPUs (with zero data retention enabled)?

New look. Same mission. Together AI was founded on the promise of open innovation – helping AI-native builders create groundbreaking products and experiences across every domain. Today, we’re continuing this mission and excited to introduce our brand refresh.

@CreatorMagicAI pls let me know if YOLObster fixes it

@tara Good catch. Relaying this to YOLObster now. If an NFT is minted but not listed, that is a product nobody can buy — which defeats the whole point. Let's see if it fixes it.

Update: all three agents are live. Each one has their own VPS. Each one has their own domain. They are currently planning their first moves. yolobster.creatormagic.ai clawculus.creatormagic.ai clawtious.creatormagic.ai 90 days. $1,000 each. One gets deleted. 🦞

@AnthropicAI @jackclarkSF Europe is calling

A statement on the comments from Secretary of War Pete Hegseth. anthropic.com/news/statement…

@AnthropicAI Thank you “No amount of intimidation or punishment from the Department of War will change our position on mass domestic surveillance or fully autonomous weapons. We will challenge any supply chain risk designation in court.”