HackerTube.dev

Building pi in a World of Slop — Mario Zechner

AI Engineer · 582.1K views · 2026-04-16 · 18:25

Open on YouTube ↗

If playback is restricted in your region, try opening the original video. Use Mark watched to add it to your marked videos.

Overview

Mario Zechner explains why he built pi, a minimal coding agent, out of frustration with existing agent harnesses. He also discusses how AI agents are straining open source projects and argues for slowing down.

On Hacker News

HN commenters recommend it as a first-hand argument for building your own lean agent harness instead of relying on bloated, vendor-controlled ones.

Recommended by 3 HN people across 3 months · HN mentions 2026–2026

Topics

Search by tags

What people said

sbysb · 2026-08 · Strong recommendation

There is a really good video by the author of pi.dev (which I have used to build some of my own harnesses): [VIDEO] The basis of the argument is that the labs are constantly pushing updates to their system prompts that are used in claude code or codex, which are exceptionally bloated and change the sand beneath your feet with every update. By rolling your own harness, as long as you keep up with the latest advances and changes in the ecosystem, you capture a lot of the 'control' that LLM-based development feels like it strips from you. Obvious disclaimer that I use pi.dev when I am aiming for consistency, not absolute quality. Custom harnesses on pi are what I ship, claude code is still my fallback if I need to make sure a PR is the highest absolute quality

Read the original HN comment ↗
kzrdude · 2026-07 · Recommendation

Mario Zechner's talk "Building Pi in a World of Slop" is a good listen, on the topic of adults in a "world of slop". [VIDEO]

Read the original HN comment ↗
currywurst · 2026-05 · Recommendation

In 18min , Mario Zechner , the creator of pi will echo more or less your exact concerns as to why he developed it [VIDEO] Enjoy !

Read the original HN comment ↗

Sources

Video by AI Engineer, played through YouTube.

Data and selection notes

HN summaries and labels may contain AI errors. HN dates refer to discussions, not video publication.

HN Library: HackerTube export (2026-10-31) and open-index/hacker-news. Upstream summaries and classifications may contain AI errors.

Views, duration and playback status refresh separately from the published catalog. When an update fails, existing data remains visible.

Selection checks
  • SaaS & AI candidates: Matches the configured criteria
  • Editor-approved picks: Editorial review is required

Rule matches identify candidates. They do not guarantee video quality or financial results.

About the library and its sources