Vibe coding complex changes in Rust
Jon Gjengset2 HN recommenders · recommended in 2 months, 2025–2026
demo · advanced · 2025–2026 on HN
Jon Gjengset spends about three hours livecoding complex changes in a Rust codebase with agentic AI tools, testing his hypothesis that AI is weak at non-pattern work. He documents where Claude Code helps and where it struggles.
Pointed to as a non-promotional, realistic long session of an experienced engineer working with AI on non-trivial code.
Up next
3 mo on HNCppCon 2015: Bjarne Stroustrup “Writing Good C++14”
CppCon
2 HN recommender · 2016–2018
1 mo on HNChange w/ Jim Keller
Tenstorrent
1 HN recommend · 2023–2023
3 mo on HND is for Debacle - The Crucial Story of Vitamin D and Human Health
Ivor Cummins
3 HN recommender · 2017–2020
3 mo on HNWhy Machines That Bend Are Better
Veritasium
3 HN recommender · 2019–2021
4 mo on HN"Performance (Really) Matters" with Emery Berger
Association for Computing Machinery (ACM)
3 HN recommender · 2022–2026
8 mo on HNAnalogy as the Core of Cognition
Stanford
7 HN recommender · 2012–2025
3 mo on HNRobust-first computing: Beyond efficiency
Dave Ackley
3 HN recommender · 2015–2025
1 mo on HNThe Story Behind Audacity
Tantacrul
3 HN recommender · 2021–2023
10 mo on HNTransformers, the tech behind LLMs | Deep Learning Chapter 5
3Blue1Brown
13 HN recommender · 2024–2026
8 mo on HNDeep Dive into LLMs like ChatGPT
Andrej Karpathy
10 HN recommender · 2025–2026
8 mo on HNLet's build GPT: from scratch, in code, spelled out.
Andrej Karpathy
14 HN recommender · 2023–2025
8 mo on HNA Hackers' Guide to Language Models
Jeremy Howard
8 HN recommender · 2023–2024
4 comments from Hacker News
Ironically, when machine learning is getting “deeper & deeper”, human learning is getting more and more impatient and shallow. I have been searching “Vibe coding” videos on YouTube that are not promoting something. And I found this one and sat down and watched the whole three hours. It does take a lot of real effort. ▶ this video
Jon Gjengset (jonhoo) Who is famously fastidious did a stream on live coding where he did something similar in terms of control. Worth of a watch if that is a style you want to explore. ▶ this video I don't have the energy to do that for most things I am writing these days which are small PoC where the vibe is fine. I suspect as you do more, you will create dev guides and testing guides that can encapsulate more of that direction so you won't need to micromanage it. If you used Gemini CLI, you picked the coding agent with the worst output. So if you got something that worked to your liking, you should try Claude.
This video [0] is relevant, though it actually supports your point - it shows Claude Code struggling with non-trivial tasks and needing significant hand-holding. I suspect videos meeting your criteria are rare because most AI coding demos either cherry-pick simple problems or skip the messy reality of maintaining real codebases. [0] ▶ this video
take a look at the replies to link eg link and ▶ this video PS, what was your last setup? performance depends a lot on the domain/model/workflow[1]; some combinations don't work at all [1] by workflow I mean: trying to oneshot a feature VS interactive exploration VS boilerplate generation