21 in 21

0xSero joins Haley Berkoe on 21 in 21 to discuss local AI, open models, and his soon-to-be-released platform for benchmarking open models and hardware (local.ai). He explains how his team benchmarks models and hardware, why local AI is becoming more capable and affordable, and why ownership and control matter as more people build their work around AI. They also discuss open-source AI culture, agentic payments, and what people can do to start experimenting with local models.

FOLLOW:

https://x.com/0xsero

https://x.com/HBerkoe

LINKS

https://local.ai

Haley Berkoe sits down with Bradley Axen, who is leading many of Block's AI initiatives, including Buzz, a new open-source collaboration platform designed for humans and AI agents to work together. He also helped create goose, the open-source AI agent that was later donated to the Agentic AI Foundation under the Linux Foundation.

They discuss how Block is using AI internally with tools like Builder Bot to help engineers navigate massive codebases, automate incident response, and collaborate more effectively. Brad also shares his thoughts on where open-source AI is headed, why model flexibility matters, and how new open source AI contributors can get involved.

FOLLOW:

https://x.com/bradleyaxen

https://github.com/baxen

https://x.com/HBerkoe

LINKS:

https://buzz.xyz

https://goose-docs.ai



TIMESTAMPS:

0:00 Introduction & Brad's journey into AI at Block

2:17 What goose is and why developers should care

3:15 Open models, local inference, and switching between providers

5:00 Do AI models perform better with their own coding harness?

6:40 Why enterprises benefit from model flexibility

8:25 Why AI inference is becoming critical infrastructure

9:16 How Block is approaching AI and open-source collaboration

10:25 Builder Bot: Block's internal AI assistant

13:50 Buzz: the future of collaborative AI workflows

15:47 Will Buzz replace Slack?

20:00 How AI is changing the role of engineers

21:45 Advice for getting started in open-source AI

24:22 Where to follow Brad's work

Mic Neale, a member of the Spiral team at Block and a core developer of goose, an open source AI agent, joins Haley Berkoe on 21 in 21 to discuss goose, Mesh LLM, and open source AI. Mic shares how goose has evolved from a desktop app and CLI into the goose Development Kit (GDK), making it easier for developers to build AI applications. He also explains how Mesh LLM pools idle compute across devices, why local models and peer-to-peer infrastructure matter, and where he sees the overlap between bitcoin and open source AI. As a longtime open source contributor, Mic closes with advice for anyone looking to get involved in open source projects.

FOLLOW:

x.com/michaelneale

x.com/HBerkoe

LINKS

goose-docs.ai

meshllm.cloud

spiral.xyz

TIMESTAMPS

0:00 Intro & welcome

1:00 Mic's background

3:35 What makes the open-source AI community different?

5:02 What is goose?

6:55 Running AI models locally with goose

8:02 Why goose was designed differently from other AI agents

10:15 Mesh LLM and sharing unused compute across devices

13:20 Could you earn money by contributing inference?

17:05 Joining Spiral and the connection to bitcoin

19:11 The overlap between open-source AI and bitcoin

20:00 Career advice for aspiring open-source developers

22:00 Why open source still matters in the AI era

23:22 Where to find Mic online

Patrick Ball, Director of Research at the Human Rights Data Analysis Group, joins Haley Berkoe on 21 in 21 to discuss how data, bitcoin, and AI can help defend human rights. Patrick explains how his team uses statistics to document mass violence, how bitcoin can help protect the integrity of human rights evidence, and why nonprofits need decentralized tools and local AI to stay resilient.

hrdag.org

On this episode of 21 in 21, Calle discusses his work on Cashu, Bitchat, and Clawi. He explores how AI agents could use bitcoin-native payments and why privacy-preserving infrastructure matters in an increasingly agentic internet. Calle also reflects on his journey down the bitcoin rabbit hole, from early work on Lightning infrastructure to building eCash systems, and shares his perspective on the evolution of AI agents.

https://x.com/callebtc

https://clawi.ai/

https://bitchat.free/

https://cashu.space/