Hacker News: davidcann

New comment by davidcann in "A way to exclude sensitive files issue still open for OpenAI Codex"

davidcann — Sun, 28 Jun 2026 18:09:41 +0000

You can block file access on macOS by running codex in a sandbox with my app: https://multitui.com

New comment by davidcann in "Apple's weird anti-nausea dots cured my car sickness"

davidcann — Wed, 17 Jun 2026 04:40:26 +0000

It works for me, but only if I hold the phone up in front of my face, basically perpendicular to the road.

New comment by davidcann in "Automating myself out of development"

davidcann — Sat, 13 Jun 2026 09:55:22 +0000

Thanks for the report. I messed up the CDN settings. It looks fixed now.

New comment by davidcann in "Automating myself out of development"

davidcann — Sat, 13 Jun 2026 08:18:59 +0000

I built this with 94% written by coding agents: https://buildermark.dev/

The complete log of all prompts and commits is here: https://demo.buildermark.dev/projects/u020uhEFtuWwPei6z6nbN

New comment by davidcann in "Ask HN: Why is the HN crowd so anti-AI?"

davidcann — Sat, 06 Jun 2026 20:31:50 +0000

Photoshop alternatives already exist and are cheap or free, like Affinity.

Why create a Final Cut Pro alternative when it’s so cheap from Apple?

Many existing apps can be mostly cloned by a small team over 6 months or a year, but the challenge is finding customers willing to switch. You still need to add something new and useful, then reach customers somehow.

New comment by davidcann in "Strace-ui, Bonsai_term, and the TUI renaissance"

davidcann — Tue, 02 Jun 2026 09:33:08 +0000

You can also sandbox TUIs, with full control of the sandbox parameters. To do this on macOS, you can use: https://multitui.com

New comment by davidcann in "Ask HN: What are you working on? (May 2026)"

davidcann — Sun, 10 May 2026 19:08:29 +0000

Buildermark calculates how much of your code is written by agents. Open source, local, and cross-platform (written in Go).

https://buildermark.dev

New comment by davidcann in "Uber torches 2026 AI budget on Claude Code in four months"

davidcann — Fri, 01 May 2026 16:45:30 +0000

> 70% of committed code originating from AI.

How are they calculating that? They could be using my tool, Buildermark, but I do t think they are: https://buildermark.dev

New comment by davidcann in "Google plans to invest up to $40B in Anthropic"

davidcann — Sat, 25 Apr 2026 00:03:52 +0000

Thanks for the feedback. I agree that it’s changing very fast, which is why my thesis is that this tooling will be needed to help everyone on the team keep up.

New comment by davidcann in "Google plans to invest up to $40B in Anthropic"

davidcann — Fri, 24 Apr 2026 23:28:33 +0000

Is your team measuring how much of your code is being written with claude and comparing amongst the team, like what works best in your codebase? How are you learning from each other?

I’m making a team version of my buildermark.dev open source project and trying to learn about how teams would like to use it.

Calculate how much of your code was written by AI

davidcann — Thu, 23 Apr 2026 10:17:14 +0000

Article URL: https://github.com/gelatinousdevelopment/buildermark

Comments URL: https://news.ycombinator.com/item?id=47873980

Points: 1

# Comments: 0

New comment by davidcann in "Claude Code to be removed from Anthropic's Pro plan?"

davidcann — Wed, 22 Apr 2026 01:23:40 +0000

To help you decide if you should keep your Claude subscription, you can see how much of your code is written by Claude Code with my project (open source, local): https://github.com/gelatinousdevelopment/buildermark

See 364 prompts that wrote 94% of Buildermark

davidcann — Wed, 15 Apr 2026 15:54:42 +0000

Article URL: https://demo.buildermark.dev/projects/u020uhEFtuWwPei6z6nbN

Comments URL: https://news.ycombinator.com/item?id=47780917

Points: 2

# Comments: 0

New comment by davidcann in "Ask HN: What Are You Working On? (April 2026)"

davidcann — Sun, 12 Apr 2026 21:46:29 +0000

I’m working on Buildermark (open source, local) that calculates how much of your code is written with coding agents.

It scans your claude and codex history to find edits and matches those to git commits (even if the code was auto-formatted).

https://buildermark.dev/

You can browse all 364 prompts that wrote 94% of the code here:

https://demo.buildermark.dev/projects/u020uhEFtuWwPei6z6nbN

Show HN: Buildermark – See how much code is by your agents (open source, local)

davidcann — Sun, 12 Apr 2026 19:19:18 +0000

I made Buildermark to see exactly how much of my code is generated by my coding agents vs what I was writing by hand. For this project, it ended up being 364 agent conversations writing 94% of the code. Browse all of those here: https://demo.buildermark.dev/

It matches edits by your coding agents (scans history in `~/.claude`, '`/.codex', etc.) with git commit diffs. It does formatting-agnostic matching to be robust against auto-formatting and reorganizing code. It's open source and local only, not even any analytics.

Everything is automatic... just run the app, open the localhost:55022 frontend, and choose the project to import.

It supports Claude Code, Codex, Gemini, and Cursor, so far. There's also a browser extension to import from cloud agents.

https://buildermark.dev

I'm also working on a Team Server to aggregate results and make the project sustainable.

Comments URL: https://news.ycombinator.com/item?id=47743339

Points: 2

# Comments: 0

New comment by davidcann in "Ask HN: What Are You Working On? (March 2026)"

davidcann — Mon, 09 Mar 2026 07:46:34 +0000

Native macOS sandbox terminal:

- UI for sandbox-exec to protect filesystem - Network sandbox per domain - Secrets filter via gitleaks - Vertical tabs option

It's highly customizable. You generate native macOS app wrappers for each terminal app, each with its own rules and customizations.

https://multitui.com

New comment by davidcann in "Agent Safehouse – macOS-native sandboxing for local agents"

davidcann — Mon, 09 Mar 2026 00:00:38 +0000

I made a native macOS app with a GUI for sandbox-exec, plus a network sandbox with per-domain filtering and secrets detection: https://multitui.com/

New comment by davidcann in "macOS's Little-Known Command-Line Sandboxing Tool (2025)"

davidcann — Sat, 28 Feb 2026 01:23:43 +0000

No, I run a separate URL detection to make links clickable. However, SwiftTerm just added link detection a few days ago and I haven’t had time to look into theirs yet.

New comment by davidcann in "Let's discuss sandbox isolation"

davidcann — Sat, 28 Feb 2026 01:14:31 +0000

My app is a macOS terminal wrapper with nice GUI for sandbox-exec and network sandbox. I just added a vertical tabs option too. https://multitui.com

New comment by davidcann in "macOS's Little-Known Command-Line Sandboxing Tool (2025)"

davidcann — Sun, 22 Feb 2026 15:57:23 +0000

Yeah, that’s understandable. Many open source macOS-only apps seem to get abandoned, so I’m trying to build something sustainable.

It uses only 3 dependencies that are very well known and widely used, so supply chain risk is minimal. That leaves me, the developer, as the main point of trust.