Peter Steinberger
steipete.me · Personal blog · on HN since 2025
Peter Steinberger, an iOS developer turned founder, writes about agentic engineering and building software with AI coding agents.
What HN saysHN commenters describe him as a well-respected developer and link his posts on agentic engineering and his shipping-at-inference-speed workflow.
44HN people shared it
18linked it in comments
35stories submitted
508story points
6 months agolast shared
2025people per year2026
Most-shared posts
- 1Shipping at Inference-Speed14 people · 12 points · first shared 2025 · 1 comments on HN
- 2Just talk to it – A way of agentic engineering5 people · 214 points · first shared 2025 · 130 comments on HN
- 3Claude Code Is My Computer4 people · 115 points · first shared 2025 · 102 comments on HN
- 4VibeTunnel: Turn Any Browser into Your Mac's Terminal4 people · 15 points · first shared 2025 · 1 comments on HN
- 5Just One More Prompt4 people · 3 points · first shared 2025 · discussion on HN
- 6Stop over-thinking AI subscriptions3 people · 47 points · first shared 2025 · 60 comments on HN
- 7The Future of Vibe Coding: Building with AI, Live and Unfiltered3 people · 3 points · first shared 2025 · 1 comments on HN
- 8The Signature Flicker3 people · 2 points · first shared 2025 · discussion on HN
- 9Self-Hosting AI Models After Claude's Usage Limits2 people · 21 points · first shared 2025 · discussion on HN
- 10Finding My Spark Again2 people · 3 points · first shared 2025 · discussion on HN
- 11Homepage2 people · first shared 2026
- 12Essential Reading for Agentic Engineers – August 20251 people · 39 points · first shared 2025 · 15 comments on HN
- 13Commanding Your Claude Code Army1 people · 17 points · first shared 2025 · 4 comments on HN
- 14OpenClaw, OpenAI and the Future1 people · 6 points · first shared 2026 · discussion on HN
- 15VibeTunnel's First AI-Anniversary1 people · 2 points · first shared 2025 · 1 comments on HN
What HN people wrote when they linked it
simonw · 2026-05-07
Yeah, Andrej thinks "agentic engineering" is a good candidate too. Note that he's not claiming to have coined it there:
> Many people have tried to come up with a better name for this to differentiate it from vibe coding, personally my current favorite "agentic engineering"
Andrej posted that on 4th of February. I first saw the term "agentic engineering" used by OpenClaw creator Peter Steinberger in October 2025 (a month before he wrote the first line of code for OpenClaw) https://steipete.me/posts/just-talk-to-it
mrshu · 2026-01-28
Peter Steinberger, the author of Clawdbot / Moltbot
https://steipete.me/
akmarinov · 2026-01-26
Peter Steinberger is a well respected developer that started out in the mobile dev community. He founded a company, then made an exit and is set for money, so he just does things for fun.
Yes, he AI generated all of it, go through his articles at https://steipete.me/ to see how he does it, it’s definitely not “vibe coding”, he does make sure that what’s being output is solid.
He was one of the people in the top charts of using Claude Code a year back, which brought around the limits we know today.
He also hosts Claude Code anonymous meetups all over the world.
He’s overall a passionate developer that cares about the thing he’s building.
jrk · 2025-10-15
If you go just a few posts back in Peter's own blog he has a video of himself doing exactly this:
https://steipete.me/posts/2025/live-coding-session-building-arena
He has posted others over the past few months, but they don't seem to be on his blog currently.
As @simonw mentions in a peer comment, Armin Ronacher also has several great streams (and he's less caffeinated and frenetic than Peter :)
andai · 2026-03-25
For reference, the creator of OpenClaw has roughly the opposite philosophy:
https://steipete.me/posts/2025/shipping-at-inference-speed
kristofferR · 2026-02-16
Yup:
https://steipete.me/posts/2025/shipping-at-inference-speed
I've also seen later tweets of his that also confirms that codex is still his choice.
ElFitz · 2026-01-29
> Yeah, the "dark factory" thing is basically unproven right now.
Isn’t that as close as "it" gets for now?
> but then I started trusting the model more and more. These days I don’t read much code anymore. I watch the stream and sometimes look at key parts, but I gotta be honest - most code I don’t read. I do know where which components are and how things are structured and how the overall system is designed, and that’s usually all that’s needed.
https://steipete.me/posts/2025/shipping-at-inference-speed
spondyl · 2026-01-27
This would seem to be inline with the development philosophy for clawdbot. I like the concept but I was put off by the lack of concern around security, specifically for something that interfaces with the internet
> These days I don’t read much code anymore. I watch the stream and sometimes look at key parts, but I gotta be honest - most code I don’t read.
I think it's fine for your own side projects not meant for others but Clawdbot is, to some degree, packaged for others to use it seems.
https://steipete.me/posts/2025/shipping-at-inference-speed
never_giveup · 2026-01-21
if my understanding is correct, @steipete is using exclusively coding agents, and imo he does a good job (see clawd)
https://steipete.me/posts/2025/shipping-at-inference-speed
dewey · 2026-01-15
Every time I read these "I've managed to control Claude Code from my phone posts", they come with some variation of "so that I can continue being on my computer" during some other activity. It's a very personal decision, but feels like on of these points where people should re-evaluate. Just because we can, doesn't mean we should.
> it was so good that I caught myself coding from my phone while out with friends… and decided that this is something I should stop, more for mental health than anything.
https://steipete.me/posts/2025/shipping-at-inference-speed
tin7in · 2026-01-06
Peter (author) talks more about LLMs as slot machines here: https://steipete.me/posts/just-one-more-prompt
fhennig · 2025-11-10
I think you're making a fair comment, but it still irks me that you're quite light on details on what the "correct" approach is supposed to be, and it irks me also because it seems to now be a pattern in the discussion.
Someone gives a detailed-ish account of what they did, and that it didn't work for them, and then there are always people in the comments saying that you were doing it wrong. Fair! But at this point, I haven't seen any good posts here on how to do it _right_.
I remember this post which got a lot of traction: https://steipete.me/posts/just-talk-to-it 8 agents in parallel and so on, but light on the details.
manmal · 2025-10-23
wahnfrieden · 2025-08-18
crcastle · 2025-07-09
More information about it here https://steipete.me/posts/2025/vibetunnel-turn-any-browser-into-your-m… but I'm still not sure I clearly understand what it does.
JimDabell · 2025-06-08
> Today on my Linux machine I can prompt an agent and have it run shell commands directly. Until Apple is able to reproduce this on their devices they're behind the curve
You can do that on a Mac today as well:
https://steipete.me/posts/2025/claude-code-is-my-computer
steveklabnik · 2025-06-05
You might find this post interesting: https://steipete.me/posts/2025/claude-code-is-my-computer
It… sure is something. I’m still thinking about if it’s horrible, visionary, or both.
steipete · 2025-06-03
You can get pretty far with much less. See https://steipete.me/posts/2025/stop-overthinking-ai-subscriptions/