Hacker News: gardnr

New comment by gardnr in "Show HN: PlanWright – A control plane for AI coding agents"

gardnr — Mon, 13 Jul 2026 21:42:19 +0000

No GH contributors. New HN account. Vibe coded in 5 commits over the last two week.

Interesting choice of model:

> Co-Authored-By: Claude Opus 4.5

> 2 weeks ago

---

Opus 4.5 was introduced in November of 2025 (8 months ago)

Opus 4.6 was introduced in February of 2026 (5 months ago)

Opus 4.7 was introduced in April of 2026 (3 months ago)

Opus 4.8 was introduced in May of 2026 (2 months ago)

From: https://github.com/Planwright/planwright/commit/c746cdcaf7e6...

New comment by gardnr in "Samsung Health app threatens data deletion if users opt out AI training"

gardnr — Mon, 13 Jul 2026 21:32:15 +0000

This is like Google Ultra for personal accounts. I signed up to see what it was like and then assumed I would be able to disable training on my data as a paid customer. The only way to disable training on paid personal accounts is to disable history (no chat logs) which makes the service much less useful for me.

For Google Workspace accounts that use the Ultra plan you can disable training while retaining history. I didn't bother signing up again. It is user-hostile.

New comment by gardnr in "LARP – Revenue infrastructure for serious founders"

gardnr — Sun, 12 Jul 2026 21:01:05 +0000

I too was nervous until I clicked through and had a read.

New comment by gardnr in "SearXNG: A free internet metasearch engine"

gardnr — Fri, 03 Jul 2026 23:23:43 +0000

It has a JSON mode that you need to enable in settings and then you can create a simple python script to interact with it or have the agent use `curl` and `jq` to interact with it.

It's at the bottom of this page: https://docs.searxng.org/admin/settings/settings_search.html

New comment by gardnr in "Popping the GPU Bubble"

gardnr — Tue, 30 Jun 2026 05:51:51 +0000

Different bubble than the one I was hoping for.

This appears to be different than the recent "Speculative Pipeline Decoding" paper: https://arxiv.org/abs/2605.30852

New comment by gardnr in "LongCat-2.0, a large-scale MoE model with 1.6T total and 48B Active"

gardnr — Tue, 30 Jun 2026 05:31:14 +0000

Dwarkesh Patel has AI/ML guests on his podcast. BoorishBears may have been referring to the Jensen Huang episode where they discuss TPUs: https://youtu.be/Hrbq66XqtCo?t=982

New comment by gardnr in "LongCat-2.0, a large-scale MoE model with 1.6T total and 48B Active"

gardnr — Tue, 30 Jun 2026 01:44:37 +0000

> The training and deployment of LongCat-2.0 are built on large-scale clusters of tens of thousands of AI ASIC superpods. Compared to the mature Nvidia GPU ecosystem, the supporting software community is still less developed. We have therefore put significant effort into building a stable, secure, and scalable infrastructure.

This is the real news story. It looks like they may have used Huawei Ascend 910C chips: https://nitter.net/teortaxesTex/status/2071708141037781407#m

New comment by gardnr in "Ask HN: Conflicted about founding engineer role"

gardnr — Thu, 18 Jun 2026 18:26:06 +0000

It really depends on your personal perspective on life. Consider the two statement and which one aligns more with yourself:

1. "It's better to regret something that you have done instead of something that you haven't done."

2. "I want to retire comfortably with a high level of confidence."

People in my life always advised me to follow the highest paying job. I'm not sure that was the right advice given my circumstances. It's really up to you.

Ask HN: What is the job market like?

gardnr — Thu, 18 Jun 2026 18:20:22 +0000

We've all heard about layoffs; what are people's actual lived experiences when it comes to the recent changes in the job market?

Comments URL: https://news.ycombinator.com/item?id=48589357

Points: 56

# Comments: 62

New comment by gardnr in "If Claude Fable stops helping you, you'll never know"

gardnr — Wed, 10 Jun 2026 05:36:16 +0000

This really sucks. Given how bad their regexes were in their leaked code, I am guessing this will get triggered all the time when I am fine tuning a model or doing work with datasets. The fact that there's no feedback means I can't trust the tools.

New comment by gardnr in "Open Code Review – An AI-powered code review CLI tool"

gardnr — Fri, 05 Jun 2026 03:08:54 +0000

How snobbish was the CEO acting?

New comment by gardnr in "Creatine raises brain energy levels and slows cognitive decline: study"

gardnr — Sun, 31 May 2026 17:30:50 +0000

Just in case anyone is thinking about trying it: 25g seems pretty high. It’s worth it to review what that means for the rest of your body before starting this regime. Kidneys are really useful organs to have working.

New comment by gardnr in "Elevated error rates on Opus 4.7"

gardnr — Fri, 15 May 2026 01:43:15 +0000

Are you using Opus? Sonnet remains as useful as it was while Opus efficacy and token burn rate has soured over the last 4 months.

New comment by gardnr in "The hypocrisy of cyberlibertarianism"

gardnr — Sun, 10 May 2026 00:07:34 +0000

I have a suspicion most Libertarians are actually something else but who haven't realized it yet. When you really dig into it: idea of private property (as in owning land and charging people rent for using it) is akin to slavery (owning people and extracting labor from them). The pre-colonial indigenous structures of managing societies were much more aligned with my internal values but they are poorly defined in modern vernacular and we don't have a good "common vocabulary" to talk about how we might want to do things in a different way.

Show HN: Keep coding agents on track with shared Git hooks

gardnr — Fri, 08 May 2026 17:05:32 +0000

You need to keep them fast and reliable or your team will hate you. Shared git hooks can be a double-edged sword. They can also prevent your agents from producing abject trash. Use `pre-commit` or `husky` and enable max-lines-per-file @ 600 lines and McCabe-style complexity at 10. You can ask your agents to use `rope` or `ts-morph` where it fits to refactor and meet the new requirements.

Add a note to our AGENTS.md/CLAUDE.md: "Make descriptive commits at reasonable intervals. Ensure the git hooks are installed. NEVER use `--no-verify` unless the user confirms first."

While you are in there add this magic too: `Use TDD "Red, green, refactor." where possible.`

Comments URL: https://news.ycombinator.com/item?id=48065889

Points: 2

# Comments: 0

New comment by gardnr in "Agents need control flow, not more prompts"

gardnr — Thu, 07 May 2026 18:17:56 +0000

This is straight outta 2023:

Agents aren't reliable; use workflows instead.

New comment by gardnr in "Claude.ai and API unavailable [fixed]"

gardnr — Thu, 30 Apr 2026 01:36:42 +0000

Here is one source that agrees: https://artificialanalysis.ai/models/capabilities/coding

New comment by gardnr in "Intel Arc Pro B70 Review"

gardnr — Wed, 29 Apr 2026 03:11:19 +0000

Same throughput with much less heat. Not sure what that extra 175w is going towards but it's diminishing returns.

New comment by gardnr in "GitHub unwanted UX change: issue links now open in a popup"

gardnr — Sun, 26 Apr 2026 18:43:09 +0000

They keep adding “fancy” UI and hijacking standard browser behaviour that is infuriating on a daily basis.

Please consider a lofi version for people that want to select text without navigating to a different page.

New comment by gardnr in "Show HN: I've built a nice home server OS"

gardnr — Fri, 24 Apr 2026 23:29:05 +0000

Looks like it may not have a package manager like apt or dnf:

> Can you please add wget, nano, $my_fav_app_omg_i_love_it to the root filesystem?

> No, not likely.

I am guessing the way to use software not already in the image is to use `docker run`.