carimura

everyone is a surgeon?

One of the big problems is that everyone wants to be an influencer and this desire is being exploited by reams of influencers using their own agents to write LLM Voice on how you too can become an influencer by using agents to write LLM Voice... get it yet?

i'm surprised at the growth of all these neoclouds given the current security risk climate...

The two in my California neighborhood actually got cut down about a month ago and one hasn't been replaced yet (still shows active on that map). My neighborhood board voted to tell the Sheriff's department NOT to replace it.

It's interesting how there's pretty strong voices on all sides of the political spectrum calling for the removal of them (for different reasons).

Norm Macdonald IS funny though....

i've heard people experiencing that... I'm on the Cursor Pro+ plan, use it fairly extensively, and haven't gone above 30% of my usage. It's possible they've been resetting and I haven't been noticing.

Ya right now I find that it's best at non-development use cases, and not everyone really has those.... I'll start posting them daily though to see if it inspires anyone.

the ability to choose models. there's a little bit of that with cursor cloud code or whatever they call it when dev work is farmed out, but it's not as configurable.

so much easier, so much less nerd foo....

It's hard to keep up with the pace of everything but looking at this site it seems like the Ollama people launched it? Or are they just purposely imitating everything about Ollama. Seems pretty infringey.

Hmm maybe I should get a steam deck to do something similar.....

My current strategy is to skip ads and skip any name that is just a jumble of letters. But the garbage producers are getting so good with AI they can create entire websites with US addresses and pictures of buildings and employees and none of it is real.

I use the term sandbox loosely. They're on a VPS running as user hermes but they share everything with each other in their own user space. I could/should probably improve this. Maybe make them their own unix user. They are separated from the root-access agent.

Obsidian is like the shared knowledge base that everyone has access to and that I can easily read/review (although I try not to too often). It has architecture stuff, go-to-market section, howtos (setting up new agents, dns backups, etc.), info on my main projects, writing, etc. It gets synced between my machine and the VPS. I also store in github as a backup occasionally (thx for reminder!).

I use the actual Buzz ios app which I was building on my own but at first glance it appears is now in the iOS store.

It depends on what you mean by sensitive personal data. I actually don't give any agents access to my main email boxes instead they access a business google workspace that is spinning up.

I do separate the agents duties somewhat to try and give them the least privileges they need to do a job, and talk to all of them through buzz, and they talk to each other (occasionally) when they need something they don't have access to.

As mentioned in the post I still do a majority of my coding at my local terminal with just bits and pieces sent to my "dev-agent" through Buzz. This is a next experiment for me - (that's a hyphen!) to offload more coding to agents.

ah forgot about the RSS feed. thanks for the complement!

that's exactly what I thought too. When I first saw Buzz I was like "oh, finally a reason to look at Nostr."

two reasons that I am moderately confident in: 1) I really want something open source, but most importantly, 2) I want something easy.

My experience trying to get Discord and/or Slack to work was painful for 1 agent, let alone the potential for hundreds.

Here's the perfect example of the power of Buzz: there was some hype today about Grok Bot so i wanted to spin it up. I did, and within like 3 minutes, I had a Grok Bot talking to my other agents in Buzz, and Buzz is definitely not a supported plugin.

buzz is how they communicate. they know about each other through a couple of ways: their own stored memory, a Mnemosyne bank, or a shared obsidian wiki. Or maybe they joined a linkedin for bots that I don't know about.

Ya I'm starting to see that agents are just "input + llm + some memory + tools + lots of cron jobs".

ya all makes sense. hoping the harness can manage some of the MCP noise. I'm using 5.6-Sol so context window is 1M.

that's news to me. for what?

ya i'm sure there are lower cost options. My droplet is 8 gigs mem which I found necessary for 6 agents.

Not yet. The agents do have access to the web but not really a proper browser. Browserbase or equivalent is next on my list.

That's neat. You could do this with Buzz by just having open room conversations with agents.

(copied from comment above)

$48/month for the droplet (could probably be cheaper on Hertzner) and $100/month for OpenAI plan. so ~$150/month but again this could be cheaper with a different VPS and using Terra/Luna.

I also have a claude max plan for coding but like I mentioned in the article coding is still separate from the agents.