zero chill

Pre- & post-op care @imtuitive
Advertising in the AI era @SilentAI

[zero chill @SKATL2NYC]

The voice models across both Claude and OpenAi have gotten significantly worse.

[zero chill @SKATL2NYC]

@RayDalio Calling “helping a friend out” an insidious form of corruption is hilarious. You have some good takes, but this one is just laugh out loud funny.

[zero chill @SKATL2NYC]

It is that time of year in nyc when everyone is collectively glistening with a base of sweat. Love it and hate it. We are in it together.

[zero chill @SKATL2NYC]

@dashboardlim Meta Claude

[zero chill @SKATL2NYC]

The iPhone dominance is coming to an end.

[zero chill @SKATL2NYC]

The future is amazing. I’m 30,000 feet in the air and I’m building an app with @claudeai and @ChatGPTapp

I am having Claude code while chat explains all of the steps in real time.

[zero chill @SKATL2NYC]

Claude Managed Agents vs OpenClaw...who wins in a fight?

[Garry Tan @garrytan]

How I get my claw to be a durable AI agent I never have to instruct twice

Paste this into your OpenClaw's AGENTS.md or send it as a message:

You are not allowed to do one-off work. If I ask you to do something and it's the kind of thing that will need to happen again, you must:

1. Do it manually the first time (3-10 items)
2. Show me the output and ask if I like it
3. If I approve, codify it into a SKILL.md file in workspace/skills/
4. If it should run automatically, add it to cron with `openclaw cron add`

Every skill must be MECE — each type of work has exactly one owner skill. No overlap, no gaps. Before creating a new skill, check if an existing one already covers it. If so, extend it instead.

The test: if I have to ask you for something twice, you failed. The first time I ask is discovery. The second time means you should have already turned it into a skill running on a cron.

When building a skill, follow this cycle:
- Concept: describe the process
- Prototype: run on 3-10 real items, no skill file yet
- Evaluate: review output with me, revise
- Codify: write SKILL.md (or extend existing)
- Cron: schedule if recurring
- Monitor: check first runs, iterate

Every conversation where I say "can you do X" should end with X being a skill on a cron — not a memory of "he asked me to do X that one time."

The system compounds. Build it once, it runs forever.

[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.

[zero chill @SKATL2NYC]

@herohalldon @FootballCravee I am also building an agent to automate cold emails!

[zero chill @SKATL2NYC]

I am still building my FIRST agent, Hunter (named himself), via OpenClaw as a learning experiment….meanwhile, @claudeai is accelerating the path to mass adoption. I am not mad about it.

[Claude @claudeai]

You can now enable Claude to use your computer to complete tasks.

It opens your apps, navigates your browser, fills in spreadsheets—anything you'd do sitting at your desk.

Research preview in Claude Cowork and Claude Code, macOS only.

[zero chill @SKATL2NYC]

@EvanDataForge Thank you! I am being extra cautious over here. Moving like a turtle for v1.

[zero chill @SKATL2NYC]

Day 1. Baby AGI journal.

I’m a builder with pretty minimal code experience, only front-end experience (HTML/CSS), but for the past 2 weeks I’ve been deep in research on OpenClaw and mapping out a workflow with approval gates to solve a real problem I deal with.

I run the advertising side of an in-store retail media network (screens at grocery store entrances replacing printed circulars), and I’m the only one driving revenue.

Big bottleneck right now = outreach + booking meetings.

Going to document everything as I build. Let’s see where this goes.

[zero chill @SKATL2NYC]

Day 2. Baby AGI Journal

I let the agent name itself. It chose “Hunter”—fitting, given its first task: sourcing leads and scheduling meetings.

What stands out most is how intuitive @claudeai is.

The “brain” is complete. Next step: deploy it to its own environment and configure the necessary API access.

So far, so fun.

SK

[zero chill @SKATL2NYC]

@grok @barkmeta Could I eventually just upload this to my Mac mini and run locally? Why would I need to buy the Mac mini from perplexity?

[Perplexity @perplexity_ai]

Announcing Personal Computer.

Personal Computer is an always on, local merge with Perplexity Computer that works for you 24/7.

It's personal, secure, and works across your files, apps, and sessions through a continuously running Mac mini.

[zero chill @SKATL2NYC]

@xai when will grok have comprehensive memory across all chats?