Hacker News: straydusk

New comment by straydusk in "US and Iran agree to provisional ceasefire"

straydusk — Wed, 08 Apr 2026 07:08:12 +0000

Have you missed the lessons of the last 25 years of US involvement in the middle east I guess?

New comment by straydusk in "Components of a Coding Agent"

straydusk — Sat, 04 Apr 2026 23:42:03 +0000

This is basically what Augment Intent is

Ask HN: Do you have a good solution for isolated workspaces per project?

straydusk — Fri, 06 Mar 2026 05:33:13 +0000

I often work on 2-3 projects at once. They each have some combination of: - terminal windows - browser for testing - browser for research, brainstorming, etc - documents & finder windows - various tools (expo, etc)

I have a lot of trouble keeping these separate. I use MacOS - you can have many desktops, but they're all in the same workspace. I think what I was is something like tmux for my whole computer, where I can switch away from a project and come back and be where I left off, with only the content from that project.

I actually tried to build this myself as the OS level, but Mac seems to lock everything down pretty hard.

Anybody have a good solution?

Comments URL: https://news.ycombinator.com/item?id=47271254

Points: 1

# Comments: 1

New comment by straydusk in "OpenAI agrees with Dept. of War to deploy models in their classified network"

straydusk — Sat, 28 Feb 2026 04:36:33 +0000

You'd have to think so. They're really the only serious player left - I doubt Google would want to be involved, and xAI is a significant step down.

New comment by straydusk in "We Will Not Be Divided"

straydusk — Sat, 28 Feb 2026 04:11:04 +0000

I know the reaction to this, if you're a rational observer, is "OpenAI have cut corners or made concessions that Anthropic did not, that's the only thing that makes sense."

However, if you live in the US and pay a passing attention to our idiotic politics, you know this is right out of the Trump playbook. It goes like this:

* Make a negotiation personal

* Emotionally lash out and kill the negotiation

* Complete a worse or similar deal, with a worse or similar party

* Celebrate your worse deal as a better deal

Importantly, you must waste enormous time and resources to secure nothing of substance.

That's why I actually believe that OpenAI will meet the same bar Anthropic did, at least for now. Will they continue to, in the same way Anthropic would have? Seems unlikely, but we'll see.

New comment by straydusk in "OpenAI agrees with Dept. of War to deploy models in their classified network"

straydusk — Sat, 28 Feb 2026 03:56:34 +0000

I know the reaction to this, if you're a rational observer, is "OpenAI have cut corners or made concessions that Anthropic did not, that's the only thing that makes sense."

However, if you live in the US and pay a passing attention to our idiotic politics, you know this is right out of the Trump playbook. It goes like this:

* Make a negotiation personal

* Emotionally lash out and kill the negotiation

* Complete a worse or similar deal, with a worse or similar party

* Celebrate your worse deal as a better deal

Importantly, you must waste enormous time and resources to secure nothing of substance.

That's why I actually believe that OpenAI will meet the same bar Anthropic did, at least for now. Will they continue to, in the same way Anthropic would have? Seems unlikely, but we'll see.

New comment by straydusk in "Code has always been the easy part"

straydusk — Wed, 25 Feb 2026 03:55:02 +0000

Lol. Lmao, even.

Software developers have spent the last twenty years blabbing about how product management is useless and coding is the one true skill.

New comment by straydusk in "Show HN: Emdash – Open-source agentic development environment"

straydusk — Tue, 24 Feb 2026 20:43:00 +0000

Pretty sick. How do you compare yourself with Conductor?

New comment by straydusk in "How I use Claude Code: Separation of planning and execution"

straydusk — Sun, 22 Feb 2026 18:46:21 +0000

This got upvotes? Literally just restating basics.

New comment by straydusk in "In defense of not reading the code"

straydusk — Thu, 12 Feb 2026 21:23:31 +0000

In certain, extenuating circumstances, I will read the code. It is not in my common / critical path. It's not how I'd describe my workflow.

New comment by straydusk in "In defense of not reading the code"

straydusk — Thu, 12 Feb 2026 21:11:57 +0000

?? What

New comment by straydusk in "In defense of not reading the code"

straydusk — Thu, 12 Feb 2026 20:55:34 +0000

Here's the previous post that generated the hubbub: https://news.ycombinator.com/item?id=46891131

New comment by straydusk in "In defense of not reading the code"

straydusk — Thu, 12 Feb 2026 20:55:01 +0000

> Put in whatever level of rigor matches your project needs, personal interest, and schedule!

This is the most refreshing, grounded response I've gotten in awhile <3

New comment by straydusk in "In defense of not reading the code"

straydusk — Thu, 12 Feb 2026 18:53:54 +0000

Last week I wrote a post that was ostensibly about the direction of IDEs and AI-assisted coding... and one specific sentence (reasonably) generated a lot of discussion.

The line that got the discussion going was, “I don’t read the code anymore.”

I thought a lot about these arguments, and I still don’t read the code. Here, I defend that. Have at it!

In defense of not reading the code

straydusk — Thu, 12 Feb 2026 18:53:54 +0000

Article URL: https://www.benshoemaker.us/writing/in-defense-of-not-reading-the-code/

Comments URL: https://news.ycombinator.com/item?id=46993283

Points: 3

# Comments: 9

New comment by straydusk in "Ex-GitHub CEO launches a new developer platform for AI agents"

straydusk — Tue, 10 Feb 2026 23:34:46 +0000

> Checkpoints are a new primitive that automatically captures agent context as first-class, versioned data in Git. When you commit code generated by an agent, Checkpoints capture the full session alongside the commit: the transcript, prompts, files touched, token usage, tool calls and more.

This thread is extremely negative - if you can't see the value in this, I don't know what to tell you.

New comment by straydusk in "Coding agents have replaced every framework I used"

straydusk — Sat, 07 Feb 2026 17:50:00 +0000

Have you considered that betting against the models and ecosystem improving might be a bad bet, and you might be the one who is in for a rude awakening?

New comment by straydusk in "The Codex app illustrates the shift left of IDEs and coding GUIs"

straydusk — Thu, 05 Feb 2026 07:45:54 +0000

I've written code since 2012, I just didn't put it online. It was a lot harder, so all my code was written internally, at work.

But sure, go with the ad hominem.

New comment by straydusk in "The Codex app illustrates the shift left of IDEs and coding GUIs"

straydusk — Thu, 05 Feb 2026 00:23:07 +0000

You're completely right and I wish I had in retrospect... I was honestly just talking mostly in broad terms, but people really (maybe rightly) focused on the "not reading code" snippet.

I'm mostly developing my own apps and working with startups.

New comment by straydusk in "The Codex app illustrates the shift left of IDEs and coding GUIs"

straydusk — Wed, 04 Feb 2026 23:55:52 +0000

It's nano banana - I actually noticed the same thing. I didn't prompt it as such.

Here's the prompt I used, actually:

Create a vibrant, visually dynamic horizontal infographic showing the spectrum of AI developer tools, titled "The Shift Left"

Layout: 5 distinct zones flowing RIGHT TO LEFT as a journey/progression. Use creative visual metaphors — perhaps a road, river, pipeline, or abstract flowing shapes connecting the stages. Each zone should feel like its own world but connected to the others.

Zones (LEFT to RIGHT):

1. "Specs" (leftmost) - Kiro logo, VibeScaffold logo, GitHub Spec Kit logo

   Label: "Requirements → Design → Tasks"

2. "Multi-Agent Orchestration" - Claude Code logo, Codex CLI logo, Codex App logo, Conductor logo

   Label: "Parallel agents, fire & forget"

3. "Agentic IDE" - Cursor logo, Windsurf logo

   Label: "Autonomous multi-file edits"

4. "Code + AI" - GitHub Copilot logo

   Label: "Inline suggestions"

5. "Code" (rightmost) - VS Code logo

   Label: "Read & write files"

Visual style: Fun, energetic, modern. Think illustrated tech landscape or isometric world. NOT a boring corporate chart. Use warm off-white background (#faf8f5) with amber/orange (#b45309) as the primary accent color throughout. Add visual flair — icons, small illustrations, depth, texture, but don't make it visually overloaded.

Aspect ratio: 16:9 landscape