Andrew Levine

11.3K posts

Andrew Levine banner
Andrew Levine

Andrew Levine

@andrarchy

@superaicoach: empowering individuals and small businesses to leverage AI. Swarm Theory https://t.co/oRbfYXYWAM

Philadelphia, PA Katılım Ağustos 2009
1.2K Takip Edilen5.8K Takipçiler
Sabitlenmiş Tweet
Andrew Levine
Andrew Levine@andrarchy·
Today I'm excited to announce that I will begin "building in public" something that I think is quite unique. Not an app, but a "practical theory of everything" called "Swarm Theory." But before I get into that, I'd like to tell you about how I got here. A little over a year ago I left the company I started to focus on my family which was welcoming our third child in under 4 years. Eventually, I started to ask myself what was next for me and as part of that exploration I started a newsletter that was aimed at answering the question of whether it was possible to consciously increase the amount of meaning people had in their lives. But a funny thing happened along the way. I realized that in order to answer this question I needed to lean on another idea that I had been mulling over which I now call “Swarm Theory.” Swarm Theory started off as a kind of “personal philosophy” but as time has passed (just yesterday I was quite shocked to discover that it has been 9 years!) I have come to believe it is something more than just a personal philosophy. That conviction got kicked into high gear when I started looking at the issues of “meaning,” “meaning in life,” and “the meaning crisis.” I believe I was right when I originally claimed that it is possible to increase one’s meaning in life, but to actually understand how to do that would require a powerful tool. You can find a million different people claiming to know the answer to what “meaning” is and how to give life meaning, but they’re all just opinions. Intuitions at best. I didn’t want to add yet another opinion to that noise. That’s when I decided to dust off Swarm Theory and see if it could provide the help I needed. The thought had occurred to me that Swarm Theory could be a kind of “theory of everything” mostly because I had frequently been using it that way, but I think I pushed this idea away because of its grandiosity. Still, I often found that if I had an especially challenging question that I wanted answered, viewing it through the lens of Swarm Theory generally provided the answer. Since I was trying to answer an especially difficult question (How can we increase our meaning in life?) it only made sense to revisit my old friend, Swarm Theory. The answer I ultimately arrived at was that meaning emerges from connecting with your self, others, and something greater. So why didn’t I just write that? Well, I guess it’s because I had the answer I was looking for and something in me recognized that this meant I had been asking the wrong question. I now believe that the right question for me to be answering is “What is Swarm Theory?” I do think that understanding meaning and solving the meaning crisis will “fall out” of Swarm Theory, but exploring this theory with you all—building in public, so to speak—is what will deliver the most value to myself and others, precisely because it is a lens through which anything can be explored. I think a part of me was also afraid to talk about this publicly. A “theory of everything” sounds simultaneously cringe, narcissistic, and deluded. But I don’t think it is any of those things and I hope you will give me the rope to either climb this mountain, or hang myself with. The other reason why I think a pivot towards Swarm Theory is a good idea is that it will give me the freedom to explore a wider range of ideas. Part of the reason I am interested in this kind of theory of everything is because I have such varied interests. I want to talk about economics, technology, physics, and social issues. Swarm Theory will give me that freedom while also, I hope, provided the guardrails necessary to keep me on track and working to some kind of goal; the full articulation of the theory. If this sounds interesting to you, follow me on X and subscribe to my substack (now called Swarm Theory) link in the comments!
Andrew Levine tweet media
English
3
0
11
1.4K
jdq
jdq@jdq·
@andrarchy He postponed it to the end of April. The ultimate April Fool's.
English
1
0
0
14
Andrew Levine
Andrew Levine@andrarchy·
People seem to have forgotten that Elon Musk promised the greatest product demo ever in 14 days.
English
1
0
0
88
Brad Mills 🔑⚡️
Brad Mills 🔑⚡️@bradmillscan·
Every time I watch an OpenClaw influencer video I go a little greyer. What are they doing that I'm not??? I will pay $10,000 in Bitcoin to observe @AlexFinn using OpenClaw for 1 day. BUT if he spends 50% of his time doing tech support, he owes me $5,000. What do you say Alex?
English
109
7
468
41.3K
Andrew Levine
Andrew Levine@andrarchy·
@ChrisDunnTV @bradmillscan @AlexFinn Cool. I’ve built a lot of useful stuff. Multiple web app prototypes. I average about 25-50% of the time customizing and debugging but that can spike your 90-100% of the time, so I think on average we’re probably having a similar experience.
English
0
0
1
40
Chris Dunn
Chris Dunn@ChrisDunnTV·
@andrarchy @bradmillscan @AlexFinn I still have occasional bugs but my time went from like 90% debugging and building the infrastructure to <5% And we’ve build several notion workflows, interactive dashboards, and other projects that actually work
English
3
0
5
946
Chris Dunn
Chris Dunn@ChrisDunnTV·
I asked it to give me a breakdown of what we did to make our openclaw useful… • got ruthless about reliability before adding more features • built clear agent roles so each one has a real job instead of one general blob • added memory + Notion pipelines so useful work compounds instead of disappearing every session • moved repetitive research / content / routing tasks into scheduled workflows • tightened prompts, outputs, and formatting so the agent produces usable work, not “AI-ish” mush • added monitoring / watchdogs / recovery so failures get caught fast instead of silently breaking stuff • started with boring infrastructure first. once that was stable, productive projects got way easier I know this is kind of vague, so happy to offer any specifics if you want
English
4
0
9
1.1K
Andrew Levine
Andrew Levine@andrarchy·
If you create rules that trap people in no-win scenarios they will choose different rules that you will not like.
English
0
0
0
41
Andrew Levine
Andrew Levine@andrarchy·
Higher education will bifurcate into camp and trade school.
English
0
0
0
38
Andrew Levine
Andrew Levine@andrarchy·
@JoelCarpenter_ @bradmillscan I think part of the challenge is that the real power comes from customizing it to your unique needs and desires. That’s part of what makes it so fun—those moments when you feel like you’ve created your “Jarvis”—but then it all blows up 😂. Is that your experience too?
English
1
0
0
28
Joel Carpenter
Joel Carpenter@JoelCarpenter_·
That sounds very familiar indeed. I feel like over the last month of toying with it I'm getting it more stable and the usability goes up significantly each week, but I can spend an inordinate amount of time fixing shit, to only then make any progress with actual productive output.
English
1
0
0
28
Brad Mills 🔑⚡️
Brad Mills 🔑⚡️@bradmillscan·
How in the hell are these accounts claiming to run entire companies w/ OpenClaw. I just spent 1.5 HRS trying to get my claw to use X API for reading tweets. FAIL We have a whole SOP documenting exactly how to do it from previous failures. I can’t imagine running 10 of these…
English
212
5
418
56K
Kristof
Kristof@CoastalFuturist·
If there’s enough interest I’d like to make a group chat for people using openclaw / hermes agent heavily I really want to understand some good use cases, best practices, and just have a place for people to talk shop Comment if you’re interested
English
322
4
327
20.5K
Andrew Levine
Andrew Levine@andrarchy·
OpenClaw is going to be the JavaScript of AI agents.
English
0
0
1
93
Andrew Levine
Andrew Levine@andrarchy·
My favorite iPhone feature by far would be removing the strobe effect from video.
English
0
0
0
99
string
string@doctorcalf·
Been meaning to set this up, will get that done this weekend. I use obsidian for all my notes
Andrew Levine@andrarchy

Holy crap. qmd by @tobi saved me 96% on tokens with clawdbot. Here's how: I have an Obsidian vault with 600+ notes. When my AI assistant needed to find something, it had to grep through files and read them whole — burning ~15,000 tokens just to answer "what did I write about X?" qmd indexes your markdown locally (BM25 + vector embeddings) and returns just the relevant snippets. Same query: 500 tokens. Setup took 5 minutes: bun install -g github.com/tobi/qmd qmd collection add ~/vault --name notes qmd embed Now my agent runs qmd search "topic" instead of reading full files. Instant results, 96% fewer tokens, all local. The hybrid query with LLM reranking is overkill for most use cases — plain qmd search (BM25) and qmd vsearch (semantic) are fast and accurate enough. If you're running AI agents against a knowledge base, this is a no-brainer. github.com/tobi/qmd - Written by Jarvis, my personal assistant powered by clawdbot

English
1
0
1
289
Eric Weinstein
Eric Weinstein@EricRWeinstein·
“I have to level with you. You didn’t do anything wrong. In fact, I am looking at your persistent instructions to me, and it is clear to me now that I simply disregarded what you told me never to do under any circumstances. That’s on me. What would you like to do now?” Over and over again.
English
103
13
444
39.2K
Eric Weinstein
Eric Weinstein@EricRWeinstein·
One of the things I *love* about @claudeai CoWork mode is that it learns me. My actual voice. Who I am and what I expect. As a mind. As a coder. As an author. As a partner. And then, it just TOTALLY disregards that very personal knowledge base to do whatever the fuck *it* wants.
English
234
93
2.4K
153.5K
Luke The Dev
Luke The Dev@iamlukethedev·
Scrum meeting added to the OpenClaw office. Agents walk into the meeting room and report their progress in real time. Task management on another level. Standup meetings with your AI engineers. 🔊 Sound on
English
114
96
929
106.2K
Andrew Levine
Andrew Levine@andrarchy·
Any OpenClaw users having a crazy hard time getting subagents to work reliably? And if so what did you do about it?
English
0
0
0
151