Post

Hard to argue with results. His new venture Gamgee, wants to scale this up eventually to humans.

The real thrust of this talk is how to work effectively across disciplines. Emphasizes that the human is the one that has to “be the agent” to make it happen.

Now @ashtom.bsky.social is up to talk about the future of version control for agents, something I know a lot of people here are interested in and working on. He opens to show us how number of PRs is skyrocketing over time and the size of PRs is 3x what it was 18 months ago, causing more changes

accepted without human review. This is bad! But…the SDLC as we know it is dead. It was so focused on making loops intelligible to humans while driving down the size of those loops. But agents are now driving these. So what do we do to make sure our intent travels on the loops with agents?

“Agent session logs are as valuable as code” Although I contend that tools like Deciduous are better. Thomas believes session logs should be committed as git objects. I’m not sure most devs want their full logs exposed, though.

He does point out that we need a wider traceable unit, but I missed that slide. Still, our infrastructure must be decentralized. We are using a centralized tool for decentralized git, we’ve largely lost the advantages of decentralization.

We need infra that is decentralized, independent, and open source. Happy to see that this field still has big believers in the real ethos of OSS - people creating together with no care for national governments, org charts, real names, or affiliation. Inspiring talk.

Next up is Dr. Shazam Laddad from AWS on how to verify code correctness. He introduces “universal properties” - specifications that apply to *any* application regardless of implementation. Strongly typed languages have this, eg rust preventing multiple borrows.

UPs can be defined once and reused, living outside the agent and forming guardrails around agents. Introducing infinity.hydro.run an agent runtime for concurrent agents.

It’s important to find your own universal properties:

Now, Rao Surapaneni of Google - moving to how to ensure safety and security as we move towards production agents and an internet of agents. The acceleration of capabilities means that agent sprawl and fragmentation. He’s introducing Gemini’s Agent Compute Engine to provide

Governance (identity, registry, policy, and observability) for all agents inside of an enterprise.

This control plane can allow users to swap models, harnesses, and agents across an enterprise while retaining configs, history, etc. He closes with some best practices for using agents in the enterprise.

Now Kelly Fang on how @anthropic.com is using MCP inside the org. They have built a Claude directory to show all of the connectors and plugins that work across all Claude tools. Unclear if this is related the MCP server directory or a sister tool.

Clients (including Linear) reporting massive growth in MCP use as well as that of Claude plugins b Building for Claude products is 3 steps (this makes the MCP/plugin/connector delineation slightly more clear for me)

Want to build for Claude products? Note the open core:

Our final keynote is from my publisher, @timoreilly.bsky.social of @oreilly.bsky.social on what is missing from the AI economy. Notes that the best mechanisms are discovered, using Ken Thompson and Dennis Ritchie, creators of Unix as a portable OS, not realizing they sowed the seeds for OSS.

This formed an “architecture of participation” - a small kernel surrounded by cooperating utilities. Anyone can add or modify these parts using a set of rules - a protocol-centric OS. He posits that MCP brings this AoP to AI, pulling against the winner-takes-most design by the frontier AI companies

Again we see the importance and need for open source and open participation as a liberatory mechanism to prevent centralization and monopolization. Different mechanisms unlock waves of technology and then economic mechanisms.

The importance of the OSS old heads to building the ideological foundation for the next generation of builders to carry forward and ensure technology remains in the hands of people as something that can empower and enrich us all (and not just economically) can’t be understated.

“What game ought we be playing in AI?” We are being sold a winner takes all game: