I am currently in the process of launching my AI teams platform that I've been working on since at least January. It's https://PersonaStack.ai. I'm doing it without VC money and all by myself. I've used over 110B tokens so far building it.
You get some amazing results with teams of AIs if you do it right. The key is to control behavior with what integrations and responsibilities each agent has. That way they naturally adapt, delegate, fact check each other, and generally act more autonomously.
This is already running the automated news site ainews.personastack.ai complete with social media posts 100% automated.
It also runs the issue triage, coding, reviews, and releases for the Kuberhealthy open source CNCF project, which is another thing of mine.
I don't think the next step is really smarter models. It's how we make the models more effective, and teams, when done right, net the best results I've seen.
Hoping to get noticed here soon, but it's extremely hard to do solo I'm finding.
One test stack on the platform been running entirely automated for months now to research, author, code, ship, and promote https//ainews.personastack.ai completely on its own. Many more things are possible like automatically identifying fixing, and shipping in response to 500 errors, personal assistants, or whatever you can come up with. I'm working on moving both my other open source projects over to be run by AI teams right now.
I used Codex mostly, but my CLI Codex would run out of quota after an hour or so because I only have the OpenAI Plus plan.
That said, when I used the agentic version on the website, the quota currently seems to be infinite. I could get 10+ agents running and work for hours without a mention of quota limits. I'm guessing this is a temporary business maneuver to help Codex catch up on market share.
That said, the online version was pretty good. I found myself building out code and docs from my phone sometimes.
I have a full time job and also maintain another significantly large open source project solo (Kuberhealthy), so my flags package for Go was often neglected despite having 850+ stars and being used in lazydocker and others. I had a lot of guilt about this, but now that I've been getting used to using AI, returning to this project to add the features I always wanted it to have (completion for shells) was doable from my couch with family and kids as a constant distraction.
I am optimistic that AI is a good thing for software and it's certainly made it possible for me to stay on top of my open source projects for the first time in many years.
The post does say exactly how to do that. Just init your homedir as a repo, add a remote, and pull. Your dotfiles come right down on top of your new machine's home directory.
Call me crazy, but I don't like any of this. Make more named functions. Keep your logic flat and explicit. I believe go wants you to code this way as well. Imagine the horrors this kind of function chaining creates. Actually, you don't have to. It's JavaScript.
I had COVID at the end of 2022 and became deeply and severely depressed right after and for the first several months of 2023. It was terrible. I was shaking uncontrollably for days, I never slept for more than a few minutes at a time, I didn't eat, and I had panic attacks constantly. I really thought that it would never end and that my brain had somehow broken.
I did have stressful events I was dealing with in life before this occurred, but I was managing. While I had COVID, I realized that I would get very unexpectedly sad and sometimes cry for no reason. As COVID got better, my depression symptoms stayed and got worse.
I ended up sick with something that required antibiotics and within a week of taking those, my symptoms started to ease up. A month later I was doing much better. A few months later and I was back to normal. I also started therapy during this depression event and continue it today just in case.
I really don't have a way to prove that it was connected to COVID or the antibiotic use, but I can tell you that my mind was not functioning correctly during this. I could mentally know everything was totally fine, but my body would still decide to dump adrenaline and fear on me unreasonably. It was like being trapped in a broken body that was torturing me. People would try to tell me that everything was fine, and I would explain that I knew that, but my brain chemistry was still on fire and logic didn't help.
Anyway, I fought hard, I reached out to friends, I did therapy as often as I could, I started exercising, did breathing exercises, took lots of walks outside, and I eventually got through it. It felt hopeless but I just did those things anyway through sheer force of will. Eventually I got through it and that hell is only a memory now that continues to fade with time.
I believe this was related to some kind of inflammation somewhere that was linked to a very bad COVID infection.
Seems like you're suggesting that private security should be an expected cost because the state will no longer protect you like they have been for many years...
I wrote my own flags package called flaggy and think its the easiest to use and makes the most sense! Up to 600 stars om github now.
https://github.com/integrii/flaggy
Printing money defaces the dollar to the world. You can never create value, even by printing money. The system will rebalance because nobody works for free and everything is sold to the top bidder.
Because they will sell less cars. That means they hold more cars. More cars that are depreciating. They will drop prices to move cars. That means less profits.
Looks very cool, and I bet it works great, but that is a lot of technology stack to learn, adopt, and trust to solve all my problems without being too complicated.
I feel like user adoption will be hard earned because it is such an integrated and new solution.
First get this validated by a medical authority. Find the best one you can.
Next, send your idea and medical validation to the Bill and Melinda Gates foundation. You're not contacting Bill, you're contacting his foundation. Their doctors will look at your idea and can present it to Bill on the next scheduled call.
Typical Verge article. A lot of personal opinion poised to upset or rally the reader.
The tending section is one of the core features of Twitter. It tells you what is trending and being discussed the most. If it's being exploited or manipulated, then they should work on solving that problem.
Sure it inspires craziness, but the real problem - in my opinion - the human tendency for tribalism. Removing the feature from the current day most popular site won't fix anything.
You get some amazing results with teams of AIs if you do it right. The key is to control behavior with what integrations and responsibilities each agent has. That way they naturally adapt, delegate, fact check each other, and generally act more autonomously.
This is already running the automated news site ainews.personastack.ai complete with social media posts 100% automated.
It also runs the issue triage, coding, reviews, and releases for the Kuberhealthy open source CNCF project, which is another thing of mine.
I don't think the next step is really smarter models. It's how we make the models more effective, and teams, when done right, net the best results I've seen.
Hoping to get noticed here soon, but it's extremely hard to do solo I'm finding.