Hacker News: luckystarr

New comment by luckystarr in "Asana cleared 5 years of engineering work in 2 weeks with Codex"

luckystarr — Thu, 20 Aug 2026 06:48:10 +0000

Apparently the task was to remove dead weight. Haven't read what they replaced "Enzyme" with.

I did subagent based removal tasks a few times. These were the ones that required the least amount of input or thinking from me, because the requirements are abundantly clear. "Remove this part of the code without breaking any other part or by porting the tests done with it onto another system."

In these situations the code acts as the bookkeeping ledger itself, and coordination complexity is almost a no-brainer.

New comment by luckystarr in "Taste Is All That's Left"

luckystarr — Fri, 07 Aug 2026 12:49:37 +0000

Taste is something you use to build the guardrails of AI over time and many paper cuts endured. Once you have a big enough set of these (call them rules) recorded, they become your development substrate. You narrow the paths the agents can take to arrive at a coherent system. If you don't do that, superficially it may look similar, but it's not and users will be able to tell.

New comment by luckystarr in "Agent-Manager: A Tmux TUI for Running Claude Code, Codex and OpenCode"

luckystarr — Thu, 30 Jul 2026 13:07:45 +0000

Shameless plug for my project, which is a bit different.

I had the problem of crashing terminals due to OOM kills and wanted to switch to a more lightweight terminal. Also I had too many of them and couldn't find the right one any more.

I thought, why not build one yourself. The result:

https://github.com/ThePixelPilgrim/kabelsalat

It has GTK tabbed, (almost) transparently tmux-backed terminals (so quitting or crashing the app and starting it up again restores the state) in colored, named groups.

I recently added Wayland app embedding to run Chrome side by side with the terminal, local to each group, but this is still a bit shaky.

Would be nice if someone would test drive it and give me some feedback. :)

New comment by luckystarr in "Una GPS smart watch – Repairable, USB-C charging, developer-friendly"

luckystarr — Wed, 29 Jul 2026 06:58:19 +0000

OS is listed as FreeRTOS.

New comment by luckystarr in "Many "serious" mathematicians are aghast"

luckystarr — Tue, 28 Jul 2026 18:31:08 +0000

https://en.wikipedia.org/wiki/Lean_(proof_assistant)

Not sure about "bugs" in that area, but there is a lot of work going on by mathematicians in formalizing and checking ever more complex proofs using proof assistants.

These systems have been tested on very complex proofs already, but well... I'm not a mathematician, just a software engineer who accepted his new role in this "new thinking order".

New comment by luckystarr in "If AI Writes All the Code, What Do the Programmers Do?"

luckystarr — Tue, 28 Jul 2026 14:19:14 +0000

And reading reports, endlessly.

New comment by luckystarr in "Many "serious" mathematicians are aghast"

luckystarr — Tue, 28 Jul 2026 14:16:36 +0000

If these proofs were output by the AI in a format readable by a proof verification system, the verification step of publishing vanishes. Then it's only valuable to check if the stated intention actually matches the proof and isn't something completely different.

New comment by luckystarr in "OpenAI and Anthropic unite against open-weight AI risks to their bottom line"

luckystarr — Thu, 23 Jul 2026 13:55:54 +0000

Then it's a case of trying to uphold the narrative?

New comment by luckystarr in "Bonsai 27B: A 27B-Class model that runs on a phone"

luckystarr — Tue, 14 Jul 2026 19:33:20 +0000

Tried it on Android and got "!!!!!!!!!!!!!" for answers.

New comment by luckystarr in "We put a Redis server inside our runtime"

luckystarr — Tue, 07 Jul 2026 13:39:46 +0000

Fair take if the user is the same person as the implementer.

If I sell software to my customers that reduces their operational complexity by me investing some code, then I don't consider it a loss.

New comment by luckystarr in "Show HN: Salt – a systems language with Z3 theorem proving in the compiler"

luckystarr — Tue, 07 Jul 2026 09:25:38 +0000

Can be that I remembered it incorrectly, as it was in 2008, but here it is:

https://se-radio.net/2008/03/episode-88-the-singularity-rese...

New comment by luckystarr in "We put a Redis server inside our runtime"

luckystarr — Sat, 04 Jul 2026 00:45:20 +0000

There is a difference between easy to set up and not having to set up anything. It's an improvement in operational UX.

New comment by luckystarr in "Europe's top court upholds Google's record $4.7B antitrust fine"

luckystarr — Thu, 02 Jul 2026 17:46:15 +0000

It only changes behaviour if the risk of having to pay outweighs the benefit. And Google won't tell what they earned through that I guess.

New comment by luckystarr in "Show HN: Salt – a systems language with Z3 theorem proving in the compiler"

luckystarr — Thu, 02 Jul 2026 17:21:08 +0000

I listened to an interview with one of the researchers. They had a component to verify "this binary will never allocate mem outside it's allowed area" and by statically verifying that they could enable high performance IPC. Also, that was the source for the decision to allow it to run on Ring 0. That's what stuck in my mind.

New comment by luckystarr in "Show HN: Salt – a systems language with Z3 theorem proving in the compiler"

luckystarr — Thu, 02 Jul 2026 15:14:51 +0000

Sounds a bit like Microsoft's Singularity project, though I don't know if they even used a proof system to ensure a program couldn't do bad stuff(TM). After verification they just let the program run in Ring 0 (kernel space) of the CPU to skip even the performance hit of the cpu's isolation.

New comment by luckystarr in "Show HN: Salt – a systems language with Z3 theorem proving in the compiler"

luckystarr — Wed, 01 Jul 2026 18:33:16 +0000

> [int overflows, etc.] No runtime cost when Z3 can prove it. Otherwise, the compiler emits a safe runtime check as fallback.

Super interesting approach. I see this eventually be integrated into future mainstream languages, though that may take a while. I suspect that the game programming crowd will try to use it first, due to the possibility to prove certain edge cases at compile time and skip the runtime cost. But perhaps this optimization drive is no longer the case because we've got bazillions of cores nowadays. I may be too old for these predictions. Cool nonetheless.

New comment by luckystarr in "Code duplication is far cheaper than the wrong abstraction (2016)"

luckystarr — Sun, 21 Jun 2026 17:16:03 +0000

How I see this:

Refactoring code to reduce the number of lines is _compression_, akin to RLE coding.

Refactoring the code to lift conceptually coherent parts is _abstraction_.

Less compression, more abstraction. Then you're fine.

New comment by luckystarr in "Ask HN: What are you working on? (June 2026)"

luckystarr — Sun, 14 Jun 2026 18:28:40 +0000

Over the last year or so I arrived at a (sort of) MQTT semantic broker that facilitates an actor architecture. It supports federation (including transitive, so proxies "just work"(TM)), transparent outbound buffering with disk overflow and encryption with the noise protocol. Building apps on top of it is a joy. Rust.

edit: ah, yes also a broker controlled component manager that can start, stop, monitor services over the mentioned broker. This is the carpet that brings the room together.

New comment by luckystarr in "Ask HN: What was your "oh shit" moment with GenAI?"

luckystarr — Sat, 06 Jun 2026 10:58:03 +0000

Then the workers wouldn't spend 20 trillion and the economy as a whole would tank.

New comment by luckystarr in "Citing 'severe' math deficits, UC faculty demand a return to SAT tests for STEM"

luckystarr — Sat, 30 May 2026 04:51:04 +0000

In most of Germany neither is required (Baden Württemberg requires non-EU citizens to pay 1.5k€ per semester). Commonly though you have to pay from 200 to 300€ administrative fees.

The harder problem is to enter Germany, but as you have EU citizenship, that's not a problem for you.