Loading video...

Video Failed to Load

Go Home

I read Pi because the code is good, it's well thought through, it's simple, it works. Armin, and Mario share their experience building Pi, and how they're thinking through their roadmap. Such an honour to sit down with amazing engineers (:

32,404 views • 1 day ago •via X (Twitter)

11 Comments

Adam Holter's profile picture
Adam Holter1 day ago

Rare footage of Sero without the blue check.

0xSero's profile picture
0xSero1 day ago

thank you for your time and all the work you do @mitsuhiko @badlogicgames

Fireply.ai's profile picture
Fireply.ai1 day ago

the hand on the chin on the left is the exact face of someone listening closely. good sign for a sit down like this

Avenged Stoic's profile picture
Avenged Stoic1 day ago

The conversation around the 9:00 mark validates a hypothesis. Models trained a year ago had far less AI code generation in them - they primarily learned from the best human code. We are seeing the early signs of “copying a copy” entropy. ChatGPT 4.1 era models was probably the turning point.

Ziwen's profile picture
Ziwen1 day ago

when did you change pfp.. I thought it was someone else lol

probably.No.One's profile picture
probably.No.One1 day ago

Omg the dream team!

Franx Merhann's profile picture
Franx Merhann1 day ago

One day, i want to be a local AI freak like u too.

Avenged Stoic's profile picture
Avenged Stoic1 day ago

This is the type of high IQ content we need! Excellent interview.

Swarogan's profile picture
Swarogan1 day ago

I use Pi along with pi-voice for quick fixes. It's great

Tom Mann's profile picture
Tom Mann1 day ago

What's the pfp

Sriram Kiron's profile picture
Sriram Kiron1 day ago

watching this right now

Related Videos

OpenClaw - the agentic software spreading like wildfire - was built on top of Pi, a minimalist, self-modifying agent. I sat down with Pi's creator, Mario Zechner and longtime Pi user (+ the creator of Flask) Armin Ronacher ⇌ to talk Pi, and their (very grounded!) takes on building with AI. Timestamps: 00:00 Intro 07:30 How Mario, Armin, and Peter Steinberger met 15:15 How 30 dev teams use AI agents: learnings 21:50 The importance of judgment 24:26 Challenges when non-engineers write code 28:30 Downsides of over-automation 32:18 Pi 48:09 OpenClaw + Pi 50:54 “Clankers” 57:32 Open source and AI 1:00:22 Complexity as the enemy 1:02:50 Building an AI-native startup 1:11:52 “Slow the F down” 1:16:40 MCPs vs. CLI 1:25:03 Predictions and staying up to date • YouTube: • Spotify: • Apple: Brought to you by: • Statsig – ⁠ The unified platform for flags, analytics, experiments, and more. • Sonar — The makers of SonarQube, the industry standard for code verification and automated code review. Try it out for yourself. • WorkOS – WorkOS gives you APIs to ship enterprise features – SSO, directory sync, RBAC, audit logs – in days, not months. Visit learn more. --- Three parts I found especially interesting in this discussion: 1. New trend: AI makes it harder for senior engineers to reject pointless complexity. Historically, senior engineers kept software complexity at bay simply by saying “no” a lot. But Armin observes that these days, more junior engineers and product managers deploy agent-scripted counterarguments when a senior colleague kicks an idea to the curb. This makes decision-making exhausting, and more bad ideas make it into production as a result. 2. It should be MUCH easier to build specialized tools for specific tasks. Different projects need different harness types because, as Mario points out, the same hammer is not ideal for every single construction job. As such, Pi is built with the goal of allowing the creation of specialized harnesses. It can modify itself so that a user can create the bespoke harness needed for any task. Mario believes it’s a preview of how self-modifiable software might look in the future. 3. Automation bias is one of the biggest risks of working with AI agents. Once devs confirm that an AI agent can produce acceptable code, they start to review its output less often, even though agents can – and do! – produce slop. Mario advises being far more sceptical with agents, and cautions that the quality of their output isn’t guaranteed, however well they performed previously.

Gergely Orosz

173,080 views • 5 months ago