Hacker News: danenania

New comment by danenania in "Show HN: Stage CLI – An easier way of reading your AI generated changes locally"

danenania — Thu, 07 May 2026 20:18:01 +0000

Cool, good to hear. I think it’s often the case even within an individual file or change that it’s 90% routine and 10% critical to review. That’s a big part of the problem in my mind.

New comment by danenania in "Show HN: Stage CLI – an easier way of reading your AI generated changes locally"

danenania — Thu, 07 May 2026 19:53:04 +0000

Interested to try this! Have you thought about separating the parts of a PR that are routine/uninteresting from the parts that are load-bearing and need more careful review?

New comment by danenania in "Show HN: Stage CLI – an easier way of reading your AI generated changes locally"

danenania — Thu, 07 May 2026 19:49:42 +0000

I mean it’s quite literally a command line interface to their tool… what else should it be called that differentiates it from a pure browser flow?

What you are describing sounds more like “TUI” than “CLI” imo. A CLI is an interface—it’s about the input step. It makes no promise about what happens after that.

New comment by danenania in "Agentic Coding Is a Trap"

danenania — Wed, 06 May 2026 04:49:37 +0000

You can’t get every detail right up front, but you can build a robust foundation from the beginning.

The argument seems to be that AI is causing managers to demand faster results, and so everything has to be a one-shotted mess of slop that just barely works. My point is that it doesn’t take much longer to build something solid instead. Implementation time and quality/robustness are not tightly coupled in the way they used to be.

New comment by danenania in "Agentic Coding Is a Trap"

danenania — Wed, 06 May 2026 01:43:00 +0000

You’re assuming that building something robustly is significantly more time consuming than the “quick and dirty” version. But that’s not really true anymore. You might need to spend another hour or two thinking through the task up front, but the implementation takes roughly the same amount of time either way.

New comment by danenania in "Agentic Coding Is a Trap"

danenania — Wed, 06 May 2026 01:31:24 +0000

Getting the model to do it is the skill.

New comment by danenania in "Agentic Coding Is a Trap"

danenania — Tue, 05 May 2026 22:43:05 +0000

Line by line is no longer what I need to think about. I think about types/schemas, architectural division, contracts between services and components, how to test thoroughly, scaling properties, security properties, and these kinds of things.

New comment by danenania in "Agentic Coding Is a Trap"

danenania — Tue, 05 May 2026 14:05:41 +0000

It takes very little time to polish now.

New comment by danenania in "Agentic Coding Is a Trap"

danenania — Tue, 05 May 2026 03:13:05 +0000

That sounds pretty much the same as it’s always been? It used to be: “Does the happy path work? Then ship it! There’s no time to make it robust or clean up tech debt.”

Now there actually is time to make things robust if you learn how to do it.

New comment by danenania in "Agentic Coding Is a Trap"

danenania — Mon, 04 May 2026 14:32:05 +0000

> thinking, abstracting, deciding how to apply your knowledge and experience, searching for information

None of this requires coding by hand. I can do those things better and faster with agents helping me. That incudes unfamiliar areas where I am effectively a junior.

New comment by danenania in "Agentic Coding Is a Trap"

danenania — Mon, 04 May 2026 14:28:54 +0000

That’s also true without AI. Engineers want more time to polish and businesses want to ship the 80/20 solution that’s good enough to sell. There's always going to be a tension there regardless of tools.

New comment by danenania in "LLMs Are Not a Higher Level of Abstraction"

danenania — Mon, 04 May 2026 03:29:56 +0000

This is a great point. We’re very much in a transitional phase on this, but I personally do see signs in my own work with agents that we are heading toward the main deliverable being a readme/docs.

The code is still important, but I could see it becoming something that humans rarely engage with.

New comment by danenania in "Agentic Coding Is a Trap"

danenania — Mon, 04 May 2026 03:12:16 +0000

If it’s broken and the dev can’t debug it, the business won’t have much of a choice.

New comment by danenania in "Agentic Coding Is a Trap"

danenania — Mon, 04 May 2026 02:42:20 +0000

If a junior builds something with agents that turns into a mess they can’t debug, that will teach them something. If they care about getting better, they will learn to understand why that happened and how to avoid it next time.

It’s not all that different than writing code directly and having it turn into a mess they can’t debug—something we all did when we were learning to program.

It is in many ways far easier to write robust, modular, and secure software with agents than by hand, because it’s now so easy to refactor and write extensive tests. There is nothing magical about coding by hand that makes it the only way to learn the principles of software design. You can learn through working with agents too.

New comment by danenania in "Elon Musk pushes out more xAI founders as AI coding effort falters"

danenania — Sun, 15 Mar 2026 04:27:23 +0000

It seems like that could change the math quite a bit, since you’d presumably be losing a lot of capacity to failures. I’d assume you would have a much higher failure rate in space, and component failure is already pretty common on earth.

New comment by danenania in "Elon Musk pushes out more xAI founders as AI coding effort falters"

danenania — Fri, 13 Mar 2026 23:42:15 +0000

What about maintenance? I’d naively assume that’s the killer.

New comment by danenania in "AI Agent Hacks McKinsey"

danenania — Wed, 11 Mar 2026 15:09:47 +0000

> I thought we might finally have a high profile prompt injection attack against a name-brand company we could point people to.

These folks have found a bunch: https://www.promptarmor.com/resources

But I guess you mean one that has been exploited in the wild?

New comment by danenania in "GPT-5.4"

danenania — Sat, 07 Mar 2026 17:17:33 +0000

tmux makes it easy for terminal based agents to talk to each other, while also letting you see output and jump into the conversation on either side. It’s a natural fit.

New comment by danenania in "GPT-5.4"

danenania — Fri, 06 Mar 2026 14:27:21 +0000

Gemini 1.5 Pro actually has 2M!

No other model from a major lab has matched it since afaik.

Edit: err, I see in the comment below mine that Grok has 2M as well. Had no idea!

New comment by danenania in "GPT-5.4"

danenania — Fri, 06 Mar 2026 14:22:42 +0000

I built a tool at work that allows claude code and codex to communicate with each other through tmux, using skills. It works quite well.