Dave @CodeOfDave

@DaveShapi So does Dot. Just install the Desktop app on a machine with those tools and enable access for Dot to that machine.

@tonysimons On the Android side you can do something close with the side loaded version of Hermes Relay. It works most of the time. I am still working on the bugs.

My read, not a fact: Anthropic gets about 80% of its revenue from enterprise customers, mostly through the API. OpenAI is more consumer-heavy, so banked resets for individual subscribers make more sense there. Anthropic has done account-wide resets, but it doesn't publish banked or purchased ones like Codex does. I'd guess that's because those resets don't do much for its core enterprise customers.

I love this! Now I want Tesla Shoes or maybe a Tesla Backpack!

Tesla @Tesla

6 days ago

Real life, baby

19K 97K 777K 97.4M 88K

It is finally starting to feel like the future.

Elon Musk @elonmusk

6 days ago

Turns out the future does have flying cars

48K 100K 834K 78.5M 64K

@tonysimons I don't need much. This should cover it.

Something else you might find interesting. My youngest discovered that some adults like displaying Lego sets but don't want to put them together so he buys them on clearance if he can, puts them together, and sells them. "Disney Adults" pay three times the retail price of a set easily just to display it in their home. He sells a lot of them to teachers at his school.

I don't think so. My kids are on their phones a lot, but they use them in different ways. My oldest likes to take things apart and build new things. He mostly watches fix-it and maker videos while trying to get something to work. My youngest watches more brain rot. But he likes money. He learned he can buy and flip things, so he buys Lego sets on FB Marketplace (with my help) and sells them. Last Christmas the local candy store paid him and a few friends to build a big Lego display for their window. They probably spend too much time on their phones. But it is about the same time I spent on Nintendo. The kids here are active. They just don't enjoy the same things I did. I worry they miss out on kid things. My dad probably said the same about me. Times change, and we change with them. We live in a VERY rural area. I am not sure how much that changes things.

My wife and I loved Six Flags Fright Fest around Halloween when we were teenagers. Our kids have zero interest. We have tried to get them to go for three years. They also have zero interest in Disney parks. I even talked to their friends' parents. I thought a group trip might change their minds. Only two kids wanted to go. I wonder if my father ever felt like the world had changed so much that he couldn't recognize it?

zerohedge @zerohedge

a week ago

*SIX FLAGS SHARES FALL 14% TO LOWEST SINCE DECEMBER 2009

14 15 272 102K 10

@JamesWalker1979 Agreed. The profile-creation skill now puts the correct soul.md in place when the profile is made, so the first job has the rules. The cron job does something else. My standard rules live in Obsidian. When I change them there, the cron job pushes the change out to every profile.

I am bad at social media. I am also bad at knowing what is worth posting. I had Grok Bot and Dot talking to my Hermes agents within hours of their release. The integrations were not perfect. They worked well enough for what I needed. Hermes has also managed my NetBox and vCenter for months. I thought those connections were obvious. I thought nobody would care how I made them work. Then I saw posts about the same things get a lot of views. So now I ask: what am I doing today that will be a hot topic three months from now? A few things on my list: 1. I am giving my agents more access to Hyper-V and Windows Sandbox. 2. Hermes builds VM templates in Hyper-V and vCenter. Sysprep was a pain. It works now. Hermes deploys its own disposable VMs the same way it deploys Docker containers. 3. I used clean-room reverse engineering to rebuild tools that help with reverse engineering. That made every other project easier. I have five clean-room projects running now. 4. Hermes makes very good offline copies of websites for those projects. Very good copies. 5. I am building a library of reverse-engineered components to reuse as building blocks in my own projects. I could keep going. None of this felt worth a post. My default thought is, "Everyone already does this. Why read about me doing it?" Then I keep seeing posts do well that I would have skipped for that exact reason. I need to recalibrate what I call obvious. Which one should I write up first?

There are a few ways to do this, but my approach is pretty simple. I install Grok Bot Desktop on a machine and give Grok access to that system using the app. You can also install Tailscale on Grok's machine, but I've found that it eventually resets and stops working. If you're running Hermes on a headless VPS, you can install Grok Bot using Hermes' "screen" feature and achieve essentially the same result. For example, I can tell Grok, "Ask AgentX to install Docker container X on server X." In this scenario, AgentX is a Hermes profile running on the same machine I've given Grok access to through the desktop application. Grok communicates with AgentX, which then handles the actual work. It's a simple way to let Grok delegate tasks to Hermes agents without needing a complicated integration.

Chat history is evidence, not my long-term system of record. My agent does the work; durable records preserve what I’ll need next week. My Obsidian vault holds knowledge, decisions, and receipts I can open later. GBrain makes that knowledge searchable, it’s a rebuildable retrieval layer, not the source of truth. Honcho adds conversation recall and user modeling to Hermes alongside its built-in memory. Before asking me to repeat myself, search the relevant records and check their sources. After meaningful work, changes, verification, or decisions queue a concise Daily Log receipt.

I posted a while back that I run three primary Hermes agents. One installed on Linux, one in Docker, and one installed on Windows. That is not one bot running three times. A Hermes profile is not a skin. It is a separate Hermes config with its own skills, memory, sessions, and profile-scoped settings. Provider or tool auth can still be shared across profiles when you reuse the same OAuth or CLI login. Do not read "profile" as "unique credentials forever." When several local profiles sit behind one Hermes process on the same host, each turn loads that profile's own Hermes state. Think profile isolation for agent config and settings. That is not an OS permission boundary. The shared Hermes gateway on that host only serves local profiles. So I still split the work by where I want the agent to live. Host shell work stays on the Linux install. Container work stays in Docker. Desktop work stays on Windows.

@dhh How very Amish of them.

@BkashJosi I don't have an opinion on what it should look like but the voice experience has to be at least as good as Dot and Grok Bot.

I posted a while back that I run three primary Hermes agents. One installed on Linux, one in Docker, and one installed on Windows. That is not one bot running three times. A Hermes profile is not a skin. It is a separate Hermes config with its own skills, memory, sessions, and profile-scoped settings. Provider or tool auth can still be shared across profiles when you reuse the same OAuth or CLI login. Do not read "profile" as "unique credentials forever." When several local profiles sit behind one Hermes process on the same host, each turn loads that profile's own Hermes state. Think profile isolation for agent config and settings. That is not an OS permission boundary. The shared Hermes gateway on that host only serves local profiles. It does not join a Linux install, a Docker install, and a Windows install into one security model. So I still split the work by where I want the agent to live. Host shell work stays on the Linux install. Container work stays in Docker. Desktop work stays on Windows. Those OS or container boundaries are separate from Hermes profile isolation. Putting an agent in Docker does not make it a safe sandbox by itself. Before you invent another profile, ask what Hermes state it needs that the others do not. If two local profiles own the same config and the same job, ask whether you actually need both.

@itsalicesoul 9 on a Commodore 64.