Hacker News: lherron

New comment by lherron in "Code mode yields a 99.2% cost reduction in our systems"

lherron — Thu, 23 Jul 2026 11:59:40 +0000

Cool but isn’t everyone already doing this? Surprised this is what I saw at top of HN this morning.

New comment by lherron in "The classifiers Anthropic puts in front of Fable are too zealous"

lherron — Wed, 08 Jul 2026 21:02:40 +0000

Worst title ever. For once I feel the HN title should NOT match the article.

New comment by lherron in "Ask HN: Is anyone using the A2A protocol?"

lherron — Thu, 18 Jun 2026 20:57:43 +0000

I uh…still use tmux send-keys. I’ll change as soon as I find a use-case it doesn’t solve. ¯\_(ツ)_/¯

New comment by lherron in "Slightly reducing the sloppiness of AI generated front end"

lherron — Fri, 12 Jun 2026 20:47:57 +0000

“Redesign the site using frotend-design skill”

https://race-to-270.vercel.app/

New comment by lherron in "Slightly reducing the sloppiness of AI generated front end"

lherron — Fri, 12 Jun 2026 18:11:00 +0000

You really have to a) use Opus and b) use the frontend-design skill for decent results.

https://github.com/anthropics/claude-code/blob/main/plugins/...

New comment by lherron in "An update on recent Claude Code quality reports"

lherron — Thu, 23 Apr 2026 21:40:13 +0000

Are they also going to refund all the extra usage api $$$ people spent in the last month?

Also I don’t know how “improving our Code Review tool” is going to improve things going forward, two of the major issues were intentional choices. No code review is going to tell them to stop making poor and compromising decisions.

New comment by lherron in "Claude Code Routines"

lherron — Wed, 15 Apr 2026 03:36:37 +0000

It’s interesting to watch Ant try to ship every value-add product feature they can while they still have the SOTA model for agentic. When an open weights equivalent to Opus 4.5’s agentic capabilities comes out, I expect massive shifts of workloads away from Claude.

Don’t get me wrong, I think their business model is still solid and they will be able to sell every token they can generate for the next couple years. They just won’t be critical path for AI diffusion anymore, which will be good for all sides.

New comment by lherron in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

lherron — Sat, 04 Apr 2026 04:41:28 +0000

Reality is Ant can supply X tokens and they see demand for 10*X tokens. So they’ll charge whatever the top 10% of users are willing to pay, and slowly degrade the value of the subscriptions until everyone has moved to another supplier or migrated to the 10% price point. The draconian ToS that they sometimes enforce is their mechanism to degrade subscription value over time. Expect agent-sdk to be next on the chopping block, moving from oauth supported to api only. When they switch it they will rightly point out the docs never explicitly said it was allowed.

New comment by lherron in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

lherron — Sat, 04 Apr 2026 04:31:32 +0000

I think maybe you are not familiar with what /loop and the Claude cron tools do.

https://code.claude.com/docs/en/scheduled-tasks

New comment by lherron in "Levels of Agentic Engineering"

lherron — Tue, 10 Mar 2026 18:41:16 +0000

I was surprised the author didn’t mention Yegge’s list (or maybe I missed it in my skim).

New comment by lherron in "I program without syntax highlighting"

lherron — Thu, 08 Jan 2026 14:28:25 +0000

Gross.

New comment by lherron in "Show HN: Terminal UI for AWS"

lherron — Mon, 05 Jan 2026 14:22:37 +0000

Oh I think you misinterpreted my comment! I am very much a fan of this, wasn't throwing shade. I am just remarking on how my side-project scope today dwarfs my side-project scope of a year or two ago.

New comment by lherron in "Show HN: Terminal UI for AWS"

lherron — Sun, 04 Jan 2026 22:32:45 +0000

Somehow every 15 line shell script I write now turns into a 50kloc bun cli or tui app. Apparently there are many such cases.

New comment by lherron in "AI helps ship faster but it produces 1.7× more bugs"

lherron — Thu, 18 Dec 2025 14:11:57 +0000

They buried the lede. The last half of the article with ways to ground your dev environment to reduce the most common issues should be its own article. (However implementing the proper techniques somewhat obviates the need for CodeRabbit, so guess it’s understandable.)

New comment by lherron in "Pricing Changes for GitHub Actions"

lherron — Tue, 16 Dec 2025 18:01:37 +0000

Why would the self-hosted runner fee be per-minute instead of per-job? I don’t get it.

New comment by lherron in "Show HN: Gemini Pro 3 imagines the HN front page 10 years from now"

lherron — Tue, 09 Dec 2025 20:04:10 +0000

Freaking awesome. You should extend clicking on a link, similar to how this article describes infinite content:

https://worksonmymachine.ai/p/solving-amazons-infinite-shelf...

New comment by lherron in "GitHub: Git operation failures"

lherron — Tue, 18 Nov 2025 21:10:43 +0000

Gemini 3 = Skynet ?

New comment by lherron in "Run interactive commands in Gemini CLI"

lherron — Thu, 23 Oct 2025 12:22:10 +0000

Gotta be better than codex literally writing a python script to edit a file multiple times in a single prompt response.

New comment by lherron in "Run interactive commands in Gemini CLI"

lherron — Thu, 23 Oct 2025 11:51:09 +0000

Building an interactive shell inside their CLI seems like a very odd technical solution. I can’t think of any use case where the same context gathering couldn’t be gleaned by examining the file/system state after the session ended, but maybe I’m missing something.

On the other hand, now that I’ve read this, I can see how having some hooks between the code agent CLIs and ghostty/etc could be extremely powerful.

New comment by lherron in "Claude Code on the web"

lherron — Mon, 20 Oct 2025 20:39:37 +0000

Still a toss-up for me which one I use. For deep work Codex (codex-high) is the clear winner, but when you need to knock out something small Claude Code (sonnet) is a workhorse.

Also CC tool usage is so much better! Many, many times I’ve seen Codex writing a python script to edit a file which seems to bypass the diff view so you don’t really know what’s going on.