Hacker News: trenchgun

New comment by trenchgun in "It’s so hard to finish an idea that is not yours and is just suggested by AI"

trenchgun — Thu, 27 Aug 2026 05:28:39 +0000

Why delete comments! Constrained grammar! Make invalid state unrepresentable.

New comment by trenchgun in "Prime Agent: A self-improving RLM agent"

trenchgun — Thu, 06 Aug 2026 06:24:49 +0000

Interesting, so they shipped slop? Succumbed to their own AI psychosis?

New comment by trenchgun in "We have proof automation now"

trenchgun — Wed, 05 Aug 2026 14:20:36 +0000

I did write small programs myself, but mostly with Claude Code. It was very pleasant to work in it with Claude Code. Implemented a shell and 40 of coreutils. Did not really get very far with proving properties of them, but had working programs. Reading Lean4 is pretty nice. Nicer to read than OCaml, almost as nice as Haskell.

New comment by trenchgun in "We have proof automation now"

trenchgun — Mon, 27 Jul 2026 08:23:24 +0000

Lean4 is a general purpose programming language.

New comment by trenchgun in "Why Software Factories Fail (or: harness engineering is not enough)"

trenchgun — Fri, 24 Jul 2026 07:19:48 +0000

CMD+F "reward hacking" -> 0 hits.

Fail.

New comment by trenchgun in "Human mathematicians are being outcounterexampled"

trenchgun — Tue, 21 Jul 2026 06:13:35 +0000

They are already proven false through Jacobian conjecture having been proved false.

New comment by trenchgun in "Solving 20 Erdős Problems with 20 Codex Accounts Running in Parallel"

trenchgun — Wed, 15 Jul 2026 14:28:53 +0000

Yes, assuming the stuff it depends on is already formalized.

New comment by trenchgun in "Show HN: Juggler – an open-source GUI coding agent, by the creator of JUCE"

trenchgun — Wed, 15 Jul 2026 04:26:01 +0000

This is a product I have wanted to exist for quite a while, and tried to create myself, but lack the skill.

Thank you for building this!

New comment by trenchgun in "Introduction to Compilers and Language Design (2021)"

trenchgun — Sun, 05 Jul 2026 16:52:42 +0000

Then it is really not about language design... I would rather recommend https://www.plai.org/

New comment by trenchgun in "The CEO of Mullvad is the main financer of the Swedish Örebro party"

trenchgun — Mon, 29 Jun 2026 17:25:31 +0000

I think mass deportation of people with wrong skin color goes beyond "stricter view on immigration"

>large scale remigration https://en.wikipedia.org/wiki/Remigration

Insert is a programming language for self-modifying code

trenchgun — Fri, 26 Jun 2026 16:02:43 +0000

Article URL: https://github.com/uellenberg/Insert

Comments URL: https://news.ycombinator.com/item?id=48688200

Points: 2

# Comments: 0

New comment by trenchgun in "Open source AI must win"

trenchgun — Sat, 13 Jun 2026 05:26:52 +0000

>But when people think of decentralized training, they don’t first think of gigantic datacenters, owned by the same company, training models across large distances. Instead, they imagine thousands of small datacenters, or individual consumers, pooling their spare compute over the internet to orchestrate a training run larger than any single actor could manage alone. Many companies are pursuing this vision: Pluralis Research, Prime Intellect and Nous Research have already successfully decentrally trained models at scale. But in practice, training decentrally over the internet has lagged far behind more centralized training. Even their largest models (Pluralis’ 8B Protocol Model, Prime Intellect’s INTELLECT-1, and Nous’ Consilience 40B) have been trained with 1,000x less compute than today’s frontier models (such as xAI’s Grok 4). https://epoch.ai/gradient-updates/how-far-can-decentralized-...

New comment by trenchgun in "xAI is looking more like a datacentre REIT than a frontier lab"

trenchgun — Mon, 08 Jun 2026 19:30:47 +0000

Yes, and then you need to have the datacenter. Do you get a permit? How long does it take to build it?

New comment by trenchgun in "Failing grades soar with AI usage, dwindling math skills in Berkeley CS classes"

trenchgun — Thu, 04 Jun 2026 07:05:21 +0000

This pattern reads heavily LLM in style, but also... that is spot on.

New comment by trenchgun in "Agentic Mfw"

trenchgun — Wed, 03 Jun 2026 06:42:39 +0000

So... you did not read it, or did not understand what you read.

New comment by trenchgun in "What are locusts and what happened to them?"

trenchgun — Sun, 31 May 2026 06:26:51 +0000

Where?

New comment by trenchgun in "Incident with Pull Requests, Issues, Git Operations and API Requests"

trenchgun — Wed, 27 May 2026 15:49:51 +0000

But everything else still works fine, right?

New comment by trenchgun in "When everyone has AI and the company still learns nothing"

trenchgun — Tue, 05 May 2026 17:29:54 +0000

Article is mostly LLM written slop.

New comment by trenchgun in "Do I belong in tech anymore?"

trenchgun — Sun, 26 Apr 2026 05:45:25 +0000

CEO observes performative work, and his inference will be that means more people need to be fired. Let only the AI native, customer obsessed 10x engineers(/ AI swarm managers) remain.

New comment by trenchgun in "Category Theory Illustrated – Orders"

trenchgun — Sat, 18 Apr 2026 17:25:10 +0000

This is LLM written comment