it's a bit hard to know what to build next or even why to build at all right now. but we musn't stop.
what to build?
the answer i think involves: big ambition, science, data, robots, value networks & storytelling
and why?
as ever, to build the world you want to see
read on:
This is it, everyone!
We released Buzz 1.0, and what an update it is.
Your people, your agents, your project, all in one place.
Plugins. Make Buzz work your way.
Plugins are the heart of Buzz. Add your own tools, pages or panels, extend conversations, and build the workspace you want. Share with your team or with the community.
Work solo. Work together.
Your own agents chats and workspaces alongside team channels. Bring others into a chat when your're ready to collaborate.
Your choice of agents.
Run Claude, Codex, Goos or Pi on your computer. Create teams of agents for different kinds of work.
Go beyond typing.
Send voice notes, jump into live audio Huddles with yuour team, or talk with supported voice-capable agents.
Ask your agents to keep and eye on things.
With attention, they can watch for updates, follow a PR's checks and reviews, and report back while buzz is running.
On top of that we released a new version of shared compute, a plugins marketplace we will be opening up soon, agents marketplace and lots more to come.
Download the new version from buzz.xyz
Enjoy!
Agentic coding is a form of machine learning. Generated code is best treated as a blackbox artifact whose behavior and generalization should be managed via empirical evaluation, like with any ML model.
Own your intelligence.
Anyone that opposes this has something to sell you (perhaps your own intelligence back to you.)
Local models need to continue proliferating. The “absolute unit” massive models may be out of reach for now locally, so your best option is to, indeed, keep your options open. Own your harness, data, connections, runtime: your agents. Embrace open source.
(30 mins later)
i used an agent in omarchy
to make a lightning wallet
..for omarchy
[using the @lexeapp SDK; which has never once failed my building needs]
but what if the utilization of local compute was actually made much, much higher because we all shared a public network for distributed inference
no need to ask what if
meshllm.cloud/
sam: local inference is a terrible allocation of scarce resources
“a lot of people want local inference, and somehow they assume that the problem is solved now because we have open-source models, we're going to be able to run them on our computers, and so we're not going to need all the stuff in the data centre
but from a global allocation perspective, actually it's quite terrible to have everybody, like, have a bunch of the world's limited supply of DRAM sitting in their own computer and being used five percent of the time
you want maximum utilisation in the cloud if you're trying to deal with this very supply-constrained environment
somehow many people's intuition is the opposite of that”
“Revisit things that failed previously (they are likely possible now). With every model release, turn the ambition dial up another notch.”
Agree 100%. I just gave AI a problem it failed at 6 months ago and the latest models succeeded. It’s such a great time to build.
it's a bit hard to know what to build next or even why to build at all right now. but we musn't stop.
what to build?
the answer i think involves: big ambition, science, data, robots, value networks & storytelling
and why?
as ever, to build the world you want to see
read on:
very weird thing happening rn
technical people are sad, they think their skills are now useless
non-technical people are desperately wishing they were more technical so they could use agents better
this was fun to build
- fork of signal
- agent built with GDK
- using open weights model
- served via e2ee mesh-llm
- via private GPU TEE
- making private search tool calls
- paid for with ₿ over LN
a cool stack of permissionless & open source tech all working together!
this was fun to build
- fork of signal
- agent built with GDK
- using open weights model
- served via e2ee mesh-llm
- via private GPU TEE
- making private search tool calls
- paid for with ₿ over LN
a cool stack of permissionless & open source tech all working together!
An agent inside Signal using decentralized compute paid for with bitcoin
@moneyball demos a fork of Signal built by @matbalez using @Mesh_LLM and @lexeapp ↓
Timestamps:
0:00 - Demo: agent inside Signal
10:51 - The economics of decentralized compute
14:39 - Running inference at home
@jack thinks bitcoin payment adoption isn’t where it could or should be. We want your ideas on how Block, Spiral, and you can improve adoption odds within 5 years. We need a shift to change our trajectory. Here’s more on our thinking. Now we want yours.
.@jack thinks bitcoin payment adoption isn’t where it should be. We want your ideas on how @Blocks, Spiral, and you can increase adoption within 5 years. Our trajectory needs changing. Here’s more on our thinking. Now we want yours: github.com/spiralxyz/bitcoin…
Dr. Alex Wissner-Gross @alexwg Oct 24 Article Chain Theory I am excited to announce Chain Theory, a new research program of mine that seeks to rebuild fundamental physics from quantum information, and its first result: a parameter-free candidate for the