HackerLangs
TopNewTrendsCommentsPastAskShowJobs

trenchgun

1,044 karmajoined 7 yıl önce

Submissions

Insert is a programming language for self-modifying code

github.com
2 points·by trenchgun·14 gün önce·0 comments

comments

trenchgun
·5 gün önce·discuss
Then it is really not about language design... I would rather recommend https://www.plai.org/
trenchgun
·11 gün önce·discuss
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
trenchgun
·28 gün önce·discuss
>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-...
trenchgun
·geçen ay·discuss
Yes, and then you need to have the datacenter. Do you get a permit? How long does it take to build it?
trenchgun
·geçen ay·discuss
This pattern reads heavily LLM in style, but also... that is spot on.
trenchgun
·geçen ay·discuss
So... you did not read it, or did not understand what you read.
trenchgun
·geçen ay·discuss
Where?
trenchgun
·geçen ay·discuss
But everything else still works fine, right?
trenchgun
·2 ay önce·discuss
Article is mostly LLM written slop.
trenchgun
·3 ay önce·discuss
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.
trenchgun
·3 ay önce·discuss
This is LLM written comment
trenchgun
·3 ay önce·discuss
How is this useful?
trenchgun
·3 ay önce·discuss
Which of the 78 copilots? https://teybannerman.github.io/strategy/2026/03/31/how-many-...
trenchgun
·3 ay önce·discuss
You’re a literature cycle behind. ‘Middle-layer shared representations exist’ is the observed phenomenon; ‘why exactly they form’ is the theory.

You are also confusing ‘mechanistic explanation still incomplete’ with ‘empirical phenomenon unestablished.’ Those are not the same thing.

PS. Em dash? So you are some LLM bot trying to bait mine HN for reasoning traces? :D
trenchgun
·3 ay önce·discuss
Yes but this is probabilistic. Skill, documentation etc help by giving it the information it needs. You are then in the more correct probability distribution. Fine for docs, tips etc, but not good enough for mandatory things.
trenchgun
·3 ay önce·discuss
Yes this + also APIs! Due to LLMs needing APIs suddenly things that were strictly behind GUI can easily opened up for programmatic use. Double edged sword, due to infosec etc concerns, but sure is nice for personal productivity automation.
trenchgun
·4 ay önce·discuss
Do you run security review by agents over this?
trenchgun
·4 ay önce·discuss
Claude default frontend skills suck :D
trenchgun
·4 ay önce·discuss
Why is it better than native x11?
trenchgun
·4 ay önce·discuss
>Such is very difficult at the moment

What do you mean? It's a nice and simple language. Way easier to get started than OCaml or Haskell for example. And LLMs write programs in Lean4 with ease as well. Only issue is that there are not as many libraries (for software, for math proofs there is plenty).

But for example I worked with Claude Code and implemented a shell + most of unix coreutils in like a couple of hours. Claude did some simple proofs as well, but that part is obvs harder. But when the program is already in Lean4, you can start moving up the verification ladder up piece by piece.