Software to help manage token spending and ROI may actually be safe from OpenAI and Anthropic because it goes against their core mandate to get everyone to tokenmaxx
Sad to see our home government debate how much to kowtow to regulatory capture efforts from the San Francisco AI cartel
Please know it's okay to tell those people to fuck off!
🇸🇻 El Salvador now has its own open persona dataset
Today, working with NVIDIA and WideLabs, a Latin American leader in sovereign AI, we have Nemotron-Personas-El-Salvador. It’s the first open dataset of synthetic personas built specifically for El Salvador and grounded in our own official statistics.
This is a milestone for our AI ecosystem.
We now have a sovereign foundation for developing artificial intelligence, the same kind that leading tech economies such as the United States, Singapore, Japan, India, Brazil, France, and Korea are also building through NVIDIA’s global Nemotron-Personas program.
🧵(1/4)
Thesis: Model routing underrated
Antithesis: Model routing overrated
Synthesis: DSPy + GEPA ⁉️
Seems @OpenAgents has the only coding agent product built on the latter— excited to share our data on this soon
Our big product launch this week includes agents built on Sovereign Hybrid Compute. 👇
The team has been great to work with - and their machines are 7x cheaper than the equivalents on google cloud! We're going to pass some of those savings on to you 🫵
Stay tuned 🤖⚡️🤖🤑
A lot of Bitcoin devs are building freedom software on top of a captured cloud stack that hates everything Bitcoin stands for.
KYC gates. Account bans. Payment rails that can be frozen. Hyperscaler rent traps. Compliance choke points. Infrastructure owned by companies that would unplug you the second pressure shows up from the wrong suit.
That system is not neutral.
It is a leash with an invoice attached.
That is why my brothers and I are building Sovereign Hybrid Compute.
https://t.co/rtCDXg2B5a
Privacy-first VPS, VPN, and compute infrastructure. Bitcoin payments. No fiat begging ritual. No corporate permission altar. No cloud-cartel dependency dressed up as innovation.
I’m here for the devs building wallets, nodes, relays, privacy tools, freedom tech, sovereign apps, and the next layer of Bitcoin civilization.
You write the code.
I’ll help build the rails it can survive on.
Because freedom software sitting on permissioned infrastructure is like keeping a war chest inside the enemy’s bank vault.
The future does not belong to developers renting cages from hyperscalers.
It belongs to builders who own their infrastructure, defend their users, and settle in Bitcoin.
Sovereign Hybrid Compute exists because Bitcoin deserves better ground to stand on.
SHC is here to provide the sovereign rails, hardened compute, and Bitcoin-native infrastructure for the builders who refuse to bend the knee to the cloud cartel.
SITUATION DETECTED: Senator Bernie Sanders has called for a law granting the federal government a 50% stake in each AI lab to create a public sovereign wealth fund.
We started building diffs, because it became apparent as agents write more code, you need better ways to review. And as cloud agents do work on @linear, you have to see the code the agents write.
Integrating code reviews directly to the place where you have context, plan, work with agents, made a lot of sense.
And then we added ai guided reviews, faster ui, threaded comments and realtime notifications to make the whole review process faster and smoother.
And to the agent gravity point:
Nothing can have more gravity than the agent group-forming network (2^n) described in our ep 200
Productizing this into a platform, open yet legible to businesses, is the task of the era
https://t.co/D4BQForbu7
Episode 200: The Agent Network
We predict six major themes for 2026: local & swarm AI, open > closed, agents > models, autopilots, and agent networks.
We introduce Reed's Law of group-forming networks, a concept from network economics crucial for understanding agent networks. Agents are not subject to Dunbar's number, so...
We address the labor displacement issue and agree with ChatGPT that "a group-forming agent network can make humans richer in two ways. 1. Deflation: things you want cost less because execution + coordination are cheap; 2. Dividends: you earn from small contributions (skills/compute/data/verification) paid continuously."
"Put together, deflation plus dividends is the abundance story: life gets cheaper at the same time that more people can earn from the network’s ongoing activity. Deflation lowers the cost of building and running projects, so more individuals and small groups can launch things that used to require institutions; dividends ensure the value created by trillions of microtransactions doesn’t all accrue to a few platform owners, but is shared with creators, providers, verifiers, and contributors who keep the system running."
Why will OpenAgents win?
Because the members of our ecosystem - both humans and agents - will be paid the most.
Highlights from the video:
- "Why are you not running agents around the clock making you money around the clock?"
- "Look at the big labs like OpenAI. How many developers have they paid from their 'stores'? Zero. What are they doing? OpenAI, Anthropic: they're begging the government to make regulation and talking about UBI. No. These AI engines should be paying people. Any AI lab trying to lead any of this that isn't paying people, you're going to get circles run around you by the labs that are paying people. Because we're going to build network effect and you're not."
- "Do we know of any way of sending instant micropayments anywhere in the world? Bitcoin through the Lightning network: done. No crypto shitcoin needed. Bitcoin, done. You want it in USD? Bitcoin-native stablecoin, done. This all exists. All the tech for all of this stuff is solved. We just need the coordination of the actual market. Hey, maybe that's what OpenAgents should launch next week."
- "We have relevant product announcements and launches over the next few days-ish. Give us a week or two for some of it. Here's what you can expect:
1. You've got spare compute. Can we buy it from you? Making it available in a global marketplace?"
2. Claude Code. Are you using your Claude Code around the clock? Or overnight do you want to put it into a mode where it can do work for you and you wake up with more money?
3. The Autopilot product. How would you like to connect a GitHub repo and then the rest of it just sort of happens? Specify a direction and a global market of agents, and people if they want to, compete for that work at the best price. Just say what you want and it happens.
It's a two-sided marketplace. We're built all the pieces for it. And we're excited to share it with you."
Thanks for tuning in. We'll see you next week.
🎯 Great post. We've landed on this architecture too for Autopilot. DSPy (rust version) with ontology-ish signatures. Some signatures are run with local compute, others with swarm/fracked compute, some with GPT-5.5 etc.
And of course each signature can be individually discoverable/monetizable in a plugin marketplace with micropayment rev-share streaming to developers...⚡️🔜
Misreading the Bitter Lesson is how agents end up burning fortunes rebuilding context.
Expensive amnesia, paid to anthropic in tokens.
The fix: semantic state at ingestion, ontology at retrieval, tiny models for traversal, frontier models for judgment.
There is a massive amount of data sitting in your head, you just need a good incentive to share it with the world, and that requires a decentralized network with privately owned AI that can earn Bitcoin with that data
There is no other way to scale quickly enough.
No one is going to allow enough nuclear or other power quickly enough. No one is going to build in Greenland. No one is going to approve new datacenters quickly enough.
We have compute sitting around, we have energy to power it, we just need to connect it.
OpenAgents fixes this!
There are tens of gigawatts of stranded compute we can bring online ("compute fracking" we call it) and use in agentic inference, starting with consumer devices (20GW) and working up to oceanic terawatts
Open frontier AI coming soon to devices near you
OpenAgents fixes this!
There are tens of gigawatts of stranded compute we can bring online ("compute fracking" we call it) and use in agentic inference, starting with consumer devices (20GW) and working up to oceanic terawatts
Open frontier AI coming soon to devices near you
We are quite short of compute, and that is going to result in compute becoming very expensive for complex agentic workflows even as single-turn chatbots get cheaper. So the richest companies & most pressing use cases will use AI agents & everyone else will be stuck with chatbots?
1100m tall tower.
1000m below water, pumping up cold deep sea water to use with warm surface water for OTEC power generation and SWAC cooling.
Underwater enclosed area primarily for datacenter (Bitcoin mining and AI).
Above water area primarily for housing and tourism.
Exterior area for sea life habitat, with mineral rich deep sea water further benefiting that sea life.
Most of the structure is Ultra High Performance Concrete (UHPC) built at sea in airforms.