Hacker News: hathawsh

New comment by hathawsh in "Over-editing refers to a model modifying code beyond what is necessary"

hathawsh — Wed, 22 Apr 2026 23:59:28 +0000

You hinted at an aspect I probably haven't considered enough: The code I'm working on already has many well-established, clean patterns and nearly all of Claude's work builds on those patterns. I would probably have a very different experience otherwise.

New comment by hathawsh in "Over-editing refers to a model modifying code beyond what is necessary"

hathawsh — Wed, 22 Apr 2026 23:28:38 +0000

I love the IDE skins analogy. Very true.

New comment by hathawsh in "Over-editing refers to a model modifying code beyond what is necessary"

hathawsh — Wed, 22 Apr 2026 23:07:42 +0000

I'm on the $200/month max plan.

New comment by hathawsh in "Over-editing refers to a model modifying code beyond what is necessary"

hathawsh — Wed, 22 Apr 2026 23:02:05 +0000

Sorry, no, and they're highly project specific anyway. I just started with the "/init" skill a few weeks ago and gradually improved it from there.

New comment by hathawsh in "Over-editing refers to a model modifying code beyond what is necessary"

hathawsh — Wed, 22 Apr 2026 22:33:16 +0000

I'm either in a minority or a silent majority. Claude Code surpasses all my expectations. When it makes a mistake like over-editing, I explain the mistake, it fixes it, and I ask it to record what it learned in the relevant project-specific skills. It rarely makes that mistake again. When the skill file gets big, I ask Claude to clean and compact it. It does a great job.

It doesn't really make sense economically for me to write software for work anymore. I'm a teacher, architect, and infrastructure maintainer now. I hand over most development to my experienced team of Claude sessions. I review everything, but so does Claude (because Claude writes thorough tests also.) It has no problem handling a large project these days.

I don't mean for this post to be an ad for Claude. (Who knows what Anthropic will do to Claude tomorrow?) I intend for this post to be a question: what am I doing that makes Claude profoundly effective?

Also, I'm never running out of tokens anymore. I really only use the Opus model and I find it very efficient with tokens. Just last week I landed over 150 non-trivial commits, all with Claude's help, and used only 1/3 of the tokens allotted for the week. The most commits I could do before Claude was 25-30 per week.

(Gosh, it's hard to write that without coming across as an ad for Anthropic. Sorry.)

New comment by hathawsh in "ChatGPT won't let you type until Cloudflare reads your React state"

hathawsh — Sun, 29 Mar 2026 22:51:02 +0000

I wonder what the PGP signing concept does to thwart people who want to profit and don't care about the public good. It seems like anyone who attends a signing party can sell their key to the highest bidder, leading to bots and spammers all over again.

New comment by hathawsh in "If you thought the code writing speed was your problem; you have bigger problems"

hathawsh — Tue, 17 Mar 2026 19:02:49 +0000

Yep, we're on the same wavelength.

New comment by hathawsh in "If you thought code writing speed was your problem you have bigger problems"

hathawsh — Tue, 17 Mar 2026 18:55:29 +0000

Also add a PR reviewer bot. Give it authority to reject the PR, but no authority to merge it. Let the AIs fight until the implementation AI and the reviewer AI come to an agreement. Also limit the number of rounds they're permitted to engage in, to avoid wasting resources. I haven't done this myself, but my naive brain thinks it's probably a good idea.

New comment by hathawsh in "Is legal the same as legitimate: AI reimplementation and the erosion of copyleft"

hathawsh — Mon, 09 Mar 2026 23:25:36 +0000

I believe the GP post is saying that if we react to the new AI-enabled environment by arbitrarily strengthening IP controls for IP owners, the greatest benefactors will almost certainly be lawyer-laden corporations, not communities, artists, or open source projects. That seems like a reasonable argument.

It seems like the answer is to adjust IP owner rights very carefully, if that's possible. It sounds very hard, though.

New comment by hathawsh in "Ladybird adopts Rust, with help from AI"

hathawsh — Mon, 23 Feb 2026 18:52:25 +0000

A lot of code is "useless" only in the sense that no one wants to buy it and it will never find its way into an end user product. On the other hand, that same code might have enormous value for education, research, planning, exploration, simulation, testing, and so on. Being able to generate reams of "useless" code is a highly desirable future.

New comment by hathawsh in "Ladybird adopts Rust, with help from AI"

hathawsh — Mon, 23 Feb 2026 18:33:28 +0000

While Rust is excellent, you must acknowledge that Rust has issues with compilation time. It also has a steep learning curve (especially around lifetimes.) It's much too early to say Rust is the "final" language, especially since AI is driving a huge shift in thinking right now.

I used to think that I would never write C code again, but when I decided recently to build something that would run on ESP32 chips, I realized there wasn't any good reason for me to use Rust yet. ESP-IDF is built on C and I can write C code just fine. C compiles quickly, it's a very simple language on the surface, and as long as you minimize the use of dynamic memory allocation and other pitfalls, it's reliable.

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

hathawsh — Sun, 22 Feb 2026 09:18:06 +0000

Several months ago, just for fun, I asked Claude (the web site, not Claude Code) to build a web page with a little animated cannon that shoots at the mouse cursor with a ballistic trajectory. It built the page in seconds, but the aim was incorrect; it always shot too low. I told it the aim was off. It still got it wrong. I prompted it several times to try to correct it, but it never got it right. In fact, the web page started to break and Claude was introducing nasty bugs.

More recently, I tried the same experiment, again with Claude. I used the exact same prompt. This time, the aim was exactly correct. Instead of spending my time trying to correct it, I was able to ask it to add features. I've spent more time writing this comment on HN than I spent optimizing this toy. https://claude.ai/public/artifacts/d7f1c13c-2423-4f03-9fc4-8...

My point is that AI-assisted coding has improved dramatically in the past few months. I don't know whether it can reason deeply about things, but it can certainly imitate a human who reasons deeply. I've never seen any technology improve at this rate.

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

hathawsh — Sun, 22 Feb 2026 08:49:01 +0000

That sounds like the recommended approach. However, there's one more thing I often do: whenever Claude Code and I complete a task that didn't go well at first, I ask CC what it learned, and then I tell it to write down what it learned for the future. It's hard to believe how much better CC has become since I started doing that. I ask it to write dozens of unit tests and it just does. Nearly perfectly. It's insane.

New comment by hathawsh in "Micropayments as a reality check for news sites"

hathawsh — Sat, 21 Feb 2026 09:36:46 +0000

Good to know. Now I think I know why micropayments for news media never took off: because people who want to read news media probably don't want to waste mental cycles on keeping track of a micropayments account. They want a set-and-forget solution with a predictable cost. If micropayments can't fit those expectations, then the market probably wants something other than the thing we're calling micropayments.

New comment by hathawsh in "Micropayments as a reality check for news sites"

hathawsh — Thu, 19 Feb 2026 21:54:06 +0000

Please help me understand better, because it feels like part of the problem has already been solved. Specifically, I've been told that the independent journalists that I watch on YouTube Premium receive a portion of my subscription fee. Is that not a form of micropayments? The system seems to work well enough for videos. Isn't there some way to adapt that kind of system to other media?

New comment by hathawsh in "Parse, Don't Validate (2019)"

hathawsh — Tue, 10 Feb 2026 19:54:57 +0000

Python has an "email object" that you should definitely use if you're going to parse email messages in any way.

https://docs.python.org/3/library/email.message.html

I imagine other languages have similar libraries. I would say static typing in scripting languages has arrived and is here to stay. It's a huge benefit for large code bases.

New comment by hathawsh in "It's Always TCP_NODELAY"

hathawsh — Tue, 23 Dec 2025 00:12:48 +0000

Ha ha, well that's a relief. I thought the article was going to say that enabling TCP_NODELAY is causing problems in distributed systems. I am one of those people who just turn on TCP_NODELAY and never look back because it solves problems instantly and the downsides seem minimal. Fortunately, the article is on my side. Just enable TCP_NODELAY if you think it's a good idea. It apparently doesn't break anything in general.

New comment by hathawsh in "Garage – An S3 object store so reliable you can run it outside datacenters"

hathawsh — Fri, 19 Dec 2025 21:00:30 +0000

Erasure coding is an interesting topic for me. I've run some calculations on the theoretical longevity of digital storage. If you assume that today's technology is close to what we'll be using for a long time, then cross-device erasure coding wins, statistically. However, if you factor in the current exponential rate of technological development, simply making lots of copies and hoping for price reductions over the next few years turns out to be a winning strategy, as long as you don't have vendor lock-in. In other words, I think you're making great choices.

New comment by hathawsh in "AI capability isn't humanness"

hathawsh — Wed, 17 Dec 2025 21:40:17 +0000

OTOH, all that data is built on patterns that evolved from many years of evolution, so I think the LLM benefits from that evolution also.

New comment by hathawsh in "Google releases its new Google Sans Flex font as open source"

hathawsh — Fri, 12 Dec 2025 20:34:27 +0000

> as well as an axis for rounded terminals (as in terminals in letters, not command-line apps).

Now I want to see a rounded terminal (as in command-line apps, not terminals in letters.) Would I type in a circle? Sounds cool.