Serendipity35

 

 Building something yourself that the world insists you should buy as a subscription feels like a victory --it feels good.

Open any tech newsletter today, the narrative is entirely about corporate gatekeeping. You are told that to participate in the "AI revolution," you need to pony up twenty or thirty dollars a month per seat for a sterile, browser-based chatbot that lives on a corporate server farm, tracks your data, and updates its personality out from under you. If you decide to go the developer route and tinker with your own integrations, you are warned of the dreaded "sticker shock"—accidental loops that can run up a hundred-dollar-a-day bill before you’ve even finished your morning coffee.

It all feels a bit like those early days of dial-up network computing.

Back then, if you wanted to access the wider digital world, you had to navigate a gauntlet of compounding costs. First, you’d pay connect-time charges to dial into a supporting public data carrier like Sprint (which operated the early Telenet network). Then, you might subscribe to an access utility just to route to non-local numbers without being billed by the minute by the phone company. And finally, once your modem successfully squealed its way through the pipe, you paid a premium, by-the-minute surcharge just to access the content and mainframe forums of CompuServe or The Source. If you lingered too long reading a thread, the meter was always running, and your monthly bill would arrive looking like a car payment. About the only survivor of that primordial era still ticking today is AOL.  And, yes, AOL Desktop Gold is still available and runs under Windows right up through Windows 11.

Today’s AI ecosystem has resurrected that exact same billing anxiety. If you set up a custom AI integration, every single turn of the conversation is billed by the character. If you ask your system to monitor a database, check your server health, or help you debug a script, the "connect-time" starts ticking, and the API charges pile up rapidly.
But by setting up a virtual private  flat-rate FreeBSD "pipe" for twenty dollars a month—the modern equivalent of finding a local, non-toll access number—and pairing it with an open-source gateway like OpenClaw, we’ve effectively bypassed those premium mainframe surcharges.
It is the modern equivalent of an offline reader for complex computing functions. Utilizing a technique called prompt caching—which essentially allows the AI to remember the context of our ongoing conversation for fractions of a penny rather than re-reading the whole book every time we speak— the billing meterhas been tamed and the data keeps flowing.

Instead of watching the meter spin up dollar signs all day, our actual daily API token costs have plummeted to mere pennies.
When you look at the actual ledger, the results are almost comical. For about one dollar a day—the combined cost of our flat-rate FreeBSD server hosting, our open-source gateway platform, and our optimized, highly active token access—we have a completely private, personal dedicated AI presence available all the time.
 

The geeky technical details of how the caching works and how the gateway maps those commands and what they all do, are subjects for a later post. For now, standing in my digital workshop, I’m just enjoying the view. It is proof that with a little consistency, a respect for pacing, and a refusal to run the race at a corporate sprint, you can still stake-out a remarkably advanced corner of the future on a lunch-money budget.

"Hack" sometimes has a bad reputation. But there are some good hacks.In technology and computing, it has two meanings:
1. Unauthorized Access (verb): To gain illegal or unauthorized access to data, a computer system, or a network (e.g., "My account got hacked").
2. Clever Code Solution (noun/verb): An elegant, clever, or quick fix in programming that solves a tricky problem.

We turn to space. NASA's Voyager 1 is still moving through interstellar space at over 35,000 miles per hour (56,000 kilometers per hour). It is 15 billion miles (about 24 billion km) away from Earth.

NASA's Jet Propulsion Lab wants it to keep going for just a bit longer.

There are two Voyagers, both launched in the late summer of 1977. They are wonderful relics. These older electronics give off waste heat - which is usually a bad thing - but it keeps practically every instrument onboard warm.

It will run out of power. That was expected to happen quite a while ago, but it keeps on going. So now, JPL is doing a critical power-saving hack on sister probe, Voyager 2. They’re toggling on and off Voyager 2’s key components across a coordinated sequence. It conserves energy but still keeps things from freezing.

Why Voyager 2? It was closer to Earth and had more power to test this hack. It worked and now they want to the hack on the farther-out Voyager 1.

What is their power supply? They both have modest nuclear power plants. These thermoelectric generators convert heat produced by the natural radioactive decay of plutonium-238 into electricity. That plutonium isotope is decaying toward its 88-year half-life, so less heat is being emitted.

The probes launched with 10 instruments apiece. Some have been powered down because they served their purpose when they were moving through the planets in our solar system.

I hope Voyager 1 makes it to November and hits a historic milestone. It passes one light-day’s distance from Earth. That is a fraction of one light-year, but it is also 173 times the distance between Earth and the Sun.

If it passes that point and stays online, it will take messages over 24 hours to reach it. Its 50th anniversary will be on September 5, 2027.

Killed by Google is a website that compiles lists of all the apps, services, and hardware Google has abandoned over the years. There are a lot. 

For example, in apps Google Earth Pro was a desktop app that gave users access to Google Earth with more advanced features. It will be about 26 years old when it ends its life.

The Tenor API service was killed about 1 month ago. It was used to search for and share GIFs from Tenor's database on other websites (notably Discord). It was about 11 years old.

In the hardware category, I have a Chromecast in a drawer even though it was killed almost 2 years ago. Chromecast was a line of digital media players that allowed users to play online content on a television. It was about 11 years old.

There is a particular kind of quiet that settles over a terminal window at 8 a.m. on a Tuesday when you are the only person on earth who can see what is happening on the other end of it. No support ticket. No status page to refresh. Just you, a config file, and a decision about who, exactly, gets to talk to the thing you just built.

I spent part of this morning doing precisely that — flipping a setting called `gateway.bind` from `loopback` to `lan`, watching a self-signed certificate mint itself into existence, and approving a device pairing request from my own phone as if I were a bouncer checking my own ID at a door I installed myself. It is, by any reasonable measure, boring infrastructure work. And it is also, I have come to think, one small answer to a question my Serendipity35 co-conspirator Ken raised in this space a few months back in 'Your AI Is Not Free'"?: if free AI makes you the product, what does *running your own* make you?

Most people's relationship with artificial intelligence today is one of tenancy, not ownership. You open ChatGPT, or Claude.ai, or the Gemini app, and you are a guest in someone else's skyscraper — a very nice skyscraper, with excellent amenities, but a skyscraper nonetheless, and the lease terms are the landlord's to write and rewrite. Your prompts, your corrections, your half-finished thoughts typed in at midnight: all of it lives on servers you will never see, governed by a privacy policy you almost certainly didn't read past the second paragraph. "Free" is a business model, not a gift, and Ken said as much in this space not long ago.

OpenClaw — the open-source project I've been quietly building on both my Mac Studio and my nexttroll.com domain this week — offers a different architecture, and it is worth walking through precisely because the architecture is the point. You run the gateway process yourself. You supply your own API keys to whichever model you choose to pay for — Anthropic, Google, whoever earns your dollar this quarter — and you pay for compute the way you pay for electricity, metered and legible, rather than a flat-rate subscription that obscures what any single conversation actually cost. Your logs, your memory files, your configuration: all of it sits as plain files on a disk I can `ls` myself, not as an abstraction behind someone else's login screen.

There is a second piece of this worth dwelling on, because it is the part that actually excited me: **Skills**. In a cloud AI product, the vendor decides what the assistant is allowed to do, and you are notified of new capabilities the way you are notified of app updates — after the fact, and without a vote. In OpenClaw, a Skill is a modular, inspectable procedure — a little packaged competence — that you add, edit, or write outright. You are not a user of a product anymore. You are closer to being the systems administrator of a very small, very personal machine — which, if you have read this blog for any length of time, you will recognize as exactly the seat I have always preferred.

None of the actual sovereignty here lives in anything glamorous. It lives in bind modes, auth tokens, TLS certificates, device pairing approvals — the unglamorous plumbing that determines who can reach your AI and what it is permitted to see. I spent a genuinely irritating stretch of this morning discovering that a browser will flatly refuse to hand over "device identity" to anything served over plain HTTP from a LAN address, because modern WebCrypto requires what's called a secure context, and no amount of arguing with a curl command changes that. The fix — self-signed TLS, a certificate warning to click through, a pairing request to approve — was ten minutes of real friction. It was also, I noticed afterward, the first time all week I understood *exactly* why a piece of software was refusing me, rather than just accepting that it had.

That, I think, is the actual shape of "AI democracy" here — and I want to be precise about what I mean by it, because it is not a claim that everyone will run an identical assistant, or that we're all about to become network engineers. It means the tools required to configure and own a working AI assistant no longer live exclusively behind a computer science degree or a corporate badge. The barrier moved. It used to be technical. Now it is largely a matter of persistence — a willingness to sit through the boring, occasionally maddening reps of learning why a thing is broken before you can fix it. I have written before about training a 5K at seventy: nobody hands you the fitness. You do the unglamorous mileage, and it accrues.

I'll concede the honest caveats, because a post that skips them isn't worth the pixels. This is real effort, not a weekend hobby — there were dead ends this week, a Rust compiler grinding through hundreds of crates in the background the whole time as a reminder that not everything gets easier. And this is not full independence, whatever the word "sovereignty" might suggest. I am still, at the end of the day, paying Anthropic for the actual intelligence doing the thinking; I have relocated the boundary of control, not abolished my dependence on a large company entirely. Self-hosting an AI gateway doesn't make you off the grid. It makes you legible to yourself, which is a smaller and more honest promise.

There's an irony sitting underneath all of this that I don't want to paper over: the assistant that helped me research and draft this very post — reading through nineteen pages of my own back catalog to get the voice roughly right, checking a Gemini API key against my own config, watching a build compile in the background — is the same private, locally-configured AI this post is about. I did not write every sentence above; I directed the machine that wrote most of them, on hardware I own, with API keys I hold, in a conversation that will live in a file on my own disk when we're done. Consider this piece Exhibit A, not just an argument.

So — not an answer, but a question worth carrying to your own terminal, wherever it happens to sit: if you actually knew, with certainty, where your last conversation with an AI physically lived — whose disk, whose jurisdiction, whose future data breach — would you have said anything differently to it?