Top all-time · #21051
Emil Burzo
Personal blog · blog.emilburzo.comprogrammingculture
Emil Burzo's personal blog at blog.emilburzo.com covers programming and culture. Since 2016, 3 different Hacker News readers have linked it 12 times, most often “Running Claude Code dangerously (safely)”. It is still writing: the last post was on 2026-06-22, and you can follow it by feed.
Too few sampled comments (2) to say how often HN recommends it.?
Why HN links it
HN commenters link this blog for a post on running Claude Code with dangerous permissions on a local machine. One commenter says they built a Vagrant setup inspired by it, and another links it as a front-page item.
Summarised by Claude from a sample of 2 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Most-linked posts?
- Running Claude Code dangerously (safely)3 people · 6 mentions · first linked 2026-01-13
What Hacker News says?
I actually experienced GPS spoofing while paragliding near Ukraine, luckily in the daytime. I don't even want to imagine it at night on a rescue mission. Condolences to the occupants. It's quite easy to say "no big deal" while calm in an office, but it's really different when you're busy flying and then there's the extra workload of trying to understand what's happening, attempting to fix it, and so on. Imagine "deb…
Comment linking /2026/06/gps-spoofing-teleported-me-to-peru-while-flying/
on “Civilian plane crash in New Mexico tied to military GPS blocking”Submitted Reverse engineering the Nest home/away API as a story · 80 points
HN discussionI'm still happy with my containment setup[1][2] on linux. The only risk that I see from the article would be the "Exfiltration through an approved domain" one. But in the VM there's (by design) nothing to exfiltrate besides the source code itself, which is less valuable these days. The major benefit for me with this setup is that the agent can do all of the dev things that I can (install packages, build/run docker i…
Comment linking /2026/01/running-claude-code-dangerously-safely/
on “The ways we contain Claude across products”Submitted GPS spoofing teleported me to Peru, mid-flight as a story · 4 points
HN discussionCan't speak for the benefits of https://nono.sh/ since I haven't used it, but a downside of using docker for this is that it gets complicated if you want the agent to be allowed to do docker stuff without giving it dangerous permissions. I have a Vagrant setup inspired by this blogpost https://blog.emilburzo.com/2026/01/running-claude-code-dange... , but a bug in VirtualBox is making one core run at 100% the entire…
Comment linking /2026/01/running-claude-code-dangerously-safely/
on “Hacking Moltbook: The AI Social Network Any Human Can Control”Submitted Running Claude Code dangerously (safely) as a story · 2 points
HN discussion> unsupervised in a VM in the cloud where the agent has root Why in the cloud and not in a local VM? I've re-discovered Vagrant and have been using it exactly for this and it's surprisingly effective for my workflows. https://blog.emilburzo.com/2026/01/running-claude-code-dange...
Comment linking /2026/01/running-claude-code-dangerously-safely/
on “Bubblewrap: A nimble way to prevent agents from accessing your .env files”Submitted Running Claude Code dangerously (safely) as a story · 1 points
HN discussionToday in first page: https://blog.emilburzo.com/2026/01/running-claude-code-dange... (discussion: https://news.ycombinator.com/item?id=46690907 ).
Comment linking /2026/01/running-claude-code-dangerously-safely/
on “How worried should I be about running LLM code on my machine?”Submitted Tracking down an old OkHttp regression as a story · 1 points
HN discussionSubmitted What does StackOverflow's personalized prediction data think of you? as a story · 1 points
HN discussionSubmitted My weight loss journey as a story · 1 points
HN discussion