Hacker News: tmach32

New comment by tmach32 in "Superpowers 6"

tmach32 — Fri, 03 Jul 2026 09:25:07 +0000

I used Superpowers for a few weeks. I ran into a couple issues:

* I wish I could turn it on selectively. Many of my requests do not require the "verification before completion" and TDD ceremony. For example, agents using stock Superpowers will go so far as to grep a file every time you ask to add something to them to verify that the edit really landed.

* While I like speccing out/designing a project before implementation (nothing new in that regard), I don't like how precisely superpowers plans out the implementation in the /writing-plans skill. It tells future agents exactly what files to edit. There are two big issues with this:

  * We need to manage context rot. If one LLM session is responsible for writing out the entire plan, we aren't solving context rot. Not only is the "smart window" of context exhausted by the time the agent is planning, eg, step 7 out of 15, but it's also dragging forward all the possibly bad ideas it had earlier. It would be better if steps were planned independently.

  * Implementation is an iterative process. You find things out as you go. Your assumptions turned out to be wrong, you realize APIs don't behave the way you thought you did, etc. This is why writing out a precise plan ahead of time is an issue – it's written without this iteration.

IMO, the strongest part of Superpowers is /subagent-driven-development. Yes, it's SUPER slow. For a laugh, you can ask it to make a change you know can be done in one line. It'll do it in one line, but it take literally an hour with all the verification. But that's sort of the point. It is _very_ deliberate. For each step, it reviews the step for both compliance and code quality, then has another agent implement the fixes, _and then it reviews the fixes again_. It does this for every step (not at the end of the project). While this might seem like overkill, it leads to code which complies with the spec far better.

Instead of writing a super detailed spec, I think I'd like /writing-plans to come up with appropriate "units" of work (sometimes called slices) and to brainstorm with the user regarding implementation, but to leave it looser than "edit this exact file in this exact way". That should leave a lot more leeway to implementation agents but still give the review agents something to check compliance against.

New comment by tmach32 in "Show HN: ZeroFS – A log-structured filesystem for S3"

tmach32 — Thu, 02 Jul 2026 14:22:11 +0000

See also: JuiceFS, S3FS, and quite a few others.

We have done loads of research into using object storage wherever we can (given how cheap it is compared to SSDs), and so far it seems like making your application object store-aware is a far surer bet than abstracting S3 behind the file system. The behavior is just too different.

I'm more interested in applications that cleverly use object storage, e.g. AutoMQ, which is quite compatible with Kafka APIs but needs no HDDs.

New comment by tmach32 in "My favorite keyboards"

tmach32 — Thu, 02 Jul 2026 12:18:07 +0000

This opinion is so quaint that it makes me smile.

For me, the #1 feature of the Advantage2 is ortho. Everything else is a distant second. I don't understand how anyone can use anything but ortho.

Yes, another layout would make your fingers travel even less, but ortho lets you reduce a lot of seeking/travel without learning anything new.

New comment by tmach32 in "CursorBench 3.1"

tmach32 — Thu, 02 Jul 2026 09:40:15 +0000

Why would anyone take this benchmark seriously? Cursor is obviously biased here. They can design it and its presentation however they want to tell the story they want to tell.

New comment by tmach32 in "GLM 5.2 beats Claude in our benchmarks"

tmach32 — Mon, 29 Jun 2026 08:33:24 +0000

I think one thing people are missing about this article is that they are arguing that the harness can make a bigger difference than the model. They aren't merely hyping GLM 5.2.

My favorite keyboards

tmach32 — Mon, 29 Jun 2026 04:41:18 +0000

Article URL: https://fabiensanglard.net/keyboards/index.html

Comments URL: https://news.ycombinator.com/item?id=48714884

Points: 139

# Comments: 140

Enough Numbers to Build a Universe

tmach32 — Sun, 28 Jun 2026 19:34:11 +0000

Article URL: https://www.stephendiehl.com/posts/universe/

Comments URL: https://news.ycombinator.com/item?id=48710733

Points: 3

# Comments: 0

New comment by tmach32 in "FUTO Swipe – A new swipe typing model"

tmach32 — Wed, 24 Jun 2026 11:02:40 +0000

They didn’t support Czech?! Until what year?

New comment by tmach32 in "A man was gifted his dream car by Kevin Mitnick, who he helped put in prison"

tmach32 — Wed, 24 Jun 2026 09:18:44 +0000

I'm not talking about scrutiny. I'm talking about crass.

New comment by tmach32 in "FUTO Swipe – A new swipe typing model"

tmach32 — Wed, 24 Jun 2026 07:09:50 +0000

Well, iOS swipe keyboard is not that bad. I would not call it “permanent suffering”. I tried gboard and swiftkey and they aren’t a giant improvement over the stock keyboard these days. They used to be.

Wrt the “occasional bug”, what happens is that sometimes (enough to make it bad) the keyboard doesn’t render at all!

New comment by tmach32 in "FUTO Swipe – A new swipe typing model"

tmach32 — Wed, 24 Jun 2026 04:57:39 +0000

For us sad iOS people, what's your favorite swiping keyboard? I just use the stock Apple one because custom keyboards can still be a little buggy (eg not loading occasionally).

New comment by tmach32 in "A man was gifted his dream car by Kevin Mitnick, who he helped put in prison"

tmach32 — Wed, 24 Jun 2026 04:52:55 +0000

Yeah, I am shocked a little, because he wasn't a monster or something. Critique is valid, but speaking with obvious resentment and disrespect about someone who died is pretty gross. Again, unless they're, like, a _monster_.

New comment by tmach32 in "HPV vaccine cuts risk of dying from cervical cancer before 30"

tmach32 — Mon, 22 Jun 2026 05:42:50 +0000

I don’t think one can sensationalise the HPV vaccine enough. Cervical cancer is too common and it’s crazy that a vaccine can greatly reduce it.

If you know any women (which is obviously not a given for HN) then you know multiple women who have had cervical cancer scares or worse.

New comment by tmach32 in "Slow breathing modulates brain function and risk behavior"

tmach32 — Sun, 21 Jun 2026 09:17:45 +0000

I've been practicing coherent breathing (6 breaths/min, equal inhalation and exhalation) to help with anxiety. I'm mostly going off a study[1] where participants who practiced coherent breathing 20 mins a day reported significantly improved outcomes weeks later.

Does anyone have advice about HRV specifically within the context of anxiety?

I've been measuring my SDNN using a Polar strap, and it hasn't really budged. However, I'm not taking that too seriously. I think my HRV is already fairly good because I bike. Anecdotally, I think the coherent breathing helps, especially if I _remember to do it in stressful moments_, not just in the morning.

[1] https://pmc.ncbi.nlm.nih.gov/articles/PMC10719279/

New comment by tmach32 in "Hyundai buys Boston Dynamics"

tmach32 — Fri, 19 Jun 2026 17:28:01 +0000

Wait, haven’t they already owned them for years? Edit: right, they’re just buying the remaining 9%.

New comment by tmach32 in "As the Job Market Stutters, Simulated Work Is Surging"

tmach32 — Wed, 17 Jun 2026 15:19:12 +0000

Always wanted to play one of these. What are people’s favorites?

I liked the progression in the truck simulator games.