Mario and Armin: internal host brief #

Introduction #

If you listened to the last Fragmented episode on self-learning harnesses, you’ll notice that evolution and understand why Pi Durable is so so interesting.

But it makes sense to look at Pi-Durable more closely and understand what’s happening there.

I’m extremely fortunate today because both Mario on the show, to help us understand more about Pi Durable….

Mario/Armin, thank you so so much for coming on the show.

In the interest of science/learning

Topic details and host prompts #

Finding the right primitives ##

While I have you right in front of me….

One of the things that’s impressed me the most about Pi, is how right it gets a lot of the primitives?

Pi Durable (8–44) ##

And now would love to jump into the main topic. Pi Durable.

Motivation (8–16) ###

  1. Durability: easier to make long-running in an unattended way | easier to implement recovery, monitoring, etc
  2. Multi-player
  3. separating the harness from the compute brings safety and scaling benefits

Durability | concept Temporal + Absurd (16–23) ####

The term “Durable” has a specific meaning in the world of software engineering. What does it mean for an agent?

If you’ve worked in a company, that has dealt with some kind of scale, this is actually a common class of problems right? You have a bunch of tasks and you need to throw them into a remote queue for processing.

Famously Temporal is an open source solution.

Durability | Surviving a crash (31–37) ####

One of the other tent-pole features of Pi Durable is

Can you walk us through that … how is Pi durable able to recover say from a forced process kill, resume and then restart.

— Recovering the same child.

e.g.

A task is suspended for a week, and its plugin changes. What happens when it resumes?

Multiplayer (23–31) ###

One of the purported features of Pi Durable is a multi-player system. Can you briefly explain this feature of Pi durable.

Multiple clients to the one agent

Pi, cannot connect multiple sessions to it.

Does Pi Durable solve this problem?

Multiple writers to one session file

One of my aha moments: I was working on my pi extension; Mario you’ll be happy to know it’s also a subagent extension….

Not very straight forward because of that ownership contract between Pi sessions right?

Self learning/improving harness (37–41) ####

Pi already has /reload. Does Pi Durable add a new dimension to how it’s able to write things on the fly, and reload it making a self-learning harness.

Keep three things separate: loading new code, recovering old work with that code, and evaluating whether the change improves behavior. Ask which are Durable capabilities and which belong to an application built on it. Do not imply that arbitrary code changes are safe or that self-learning is supplied out of the box.

DEEP CUT — Can the agent inspect its own machinery? What does explicit task state let an agent understand or change about its own work that an opaque execution loop would hide? Ask for one demonstrated example and its limits.

Bringing it together: what am I building with Durable? (41–44) ####

Let’s bring it together for us: main features:

  1. Durable workflows - Surviving Crashes + Long running tasks - resuming tasks
  2. Enable Multiplayer ecosystems - Both multiple clients to agent + multiple writers to the same session
  3. Self improving-learning harnesses

Design decision

Product direction and Earendil (49–53) ###

Today, it’s a library….

?? Personal agents (44–49) ###

Quick: why is everyone doing this now, including Mario?

Lead: Why are developers building their own personal agents now, and what does Durable make easier?

5. Rapid fire (53–60) ###

  1. Will Pi ever ship an official GUI?
  2. Is Code Mode as Pi’s only tool the future? Do you use Pi that way yourselves?
  3. What’s the best advice you’ve received as a software engineer?
  4. What’s the best advice you’d give a software engineer today?
  5. How do you think software engineering will change?