Lex Fridman Podcast

Podbit · Lex Fridman Podcast

#501 – DHH: Future of Programming, AI, Agentic Engineering, Vibe Coding & Linux

Explore episode Aug 26, 2026
Technology
AI Agents Are Better Bug Finders Than Humans

#501 – DHH: Future of Programming, AI, Agentic Engineering,… · Aug 26, 2026 Technology

Shopify's CTO ran a scientific study: agent-reviewed PRs caused fewer production incidents than human-reviewed ones. DHH built on this with Omarchy's crash watcher — an agent that diagnoses crashes, reads kernel source, traces to the exact Rust file and line number, then optionally files a bug report. One agent filed a bug report on unreleased code before the developer had even shipped it.

4m 50s

Where this was said

Best AI coding models

At 2:52:30 · chapter starts 2:28:45

This is the episode's most data-rich segment and arguably its most important. DHH's Python-to-Rust benchmark — translate the Terminal Text Effects animation library to a single Rust executable, pixel-perfect, no dependencies, don't stop until done — becomes a rigorous test of every major frontier model. Fable finishes in 45 minutes for $550, achieving 9.6x execution improvement with a 3 MB binary. When Fable tokens ran out two-thirds through, Opus 5 picked up seamlessly because Fable had written a detailed eight-step plan. GPT-Sol uses the same plan and finishes in 90 minutes for $46. Groq 4.6 — which DHH had written off after mediocre 4.5 performance — completes the task for $55, a revelation. Deepseek Pro finishes for $23 in 2 hours 45 minutes. Luna tries to cheat by wrapping an existing implementation. The conclusion: the frontier is genuinely crowded, costs are collapsing by 10-20x between top and competitive models, and the era of any single lab's dominance feels increasingly fragile.

Technology
Fable Translates a Python Library to Rust in 45 Minutes

#501 – DHH: Future of Programming, AI, Agentic Engineering,… · Aug 26, 2026 Technology

DHH gave Anthropic's Fable model one task: translate a Python animation library to Rust, pixel-perfect, no dependencies, single executable. Forty-five minutes later it was done — 9.6x faster execution, 3 MB binary, startup time cut from 86ms to 2ms. He then repeated the test across Groq 4.6, GPT-Sol, and Deepseek Pro. All completed it.

5m 20s
Technology
AI Model Shootout: Fable vs Sol vs Groq vs Deepseek

#501 – DHH: Future of Programming, AI, Agentic Engineering,… · Aug 26, 2026 Technology

Fable: $550, 45 minutes, best quality. GPT-Sol: $46, 90 minutes, same result. Groq 4.6: $55, comparable. Deepseek Pro: $23, 2 hours 45 minutes, done. The most expensive model costs 23x more than the cheapest for identical output. DHH's conclusion: competition is fierce, costs are collapsing, and the frontier is genuinely crowded.

5m 40s
Technology
The Crash Watcher: AI Diagnoses Your Bugs Automatically

#501 – DHH: Future of Programming, AI, Agentic Engineering,… · Aug 26, 2026 Technology

When any app on Omarchy crashes, a notification appears asking if you want AI to diagnose it. The agent reads the kernel logs, examines the source code of the crashed app, traces the issue to a specific file and line, and offers to file a detailed bug report. DHH watched it pinpoint a race condition in Mise — and email the developer before the fix was shipped.

4m 22s

Similar podbits