Viewing profile — trenchgun
trenchgun
HN member- Joined
- Mon, Oct 28, 2019, 1:51 PM UTC
- HN karma
- 1,047
- Public activity
- 560 items
- HN profile
- View on Hacker News ↗
About trenchgun
No profile information was provided.
Recent public activity
-
comment
Comment #49193175
Interesting, so they shipped slop? Succumbed to their own AI psychosis?
-
comment
Comment #49183342
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 ver…
-
comment
Comment #49066617
Lean4 is a general purpose programming language.
-
comment
Comment #49032207
CMD+F "reward hacking" -> 0 hits. Fail.
-
comment
Comment #48988686
They are already proven false through Jacobian conjecture having been proved false.
-
comment
Comment #48921396
Yes, assuming the stuff it depends on is already formalized.
-
comment
Comment #48916308
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!
-
comment
Comment #48795693
Then it is really not about language design... I would rather recommend https://www.plai.org/
-
comment
Comment #48722183
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
- story
-
comment
Comment #48513605
>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 i…
-
comment
Comment #48450412
Yes, and then you need to have the datacenter. Do you get a permit? How long does it take to build it?
-
comment
Comment #48395114
This pattern reads heavily LLM in style, but also... that is spot on.
-
comment
Comment #48380735
So... you did not read it, or did not understand what you read.
-
comment
Comment #48343477
Where?
-
comment
Comment #48296072
But everything else still works fine, right?
-
comment
Comment #48025704
Article is mostly LLM written slop.
-
comment
Comment #47907691
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) rema…
-
comment
Comment #47817683
This is LLM written comment
-
comment
Comment #47817630
How is this useful?
-
comment
Comment #47658024
Which of the 78 copilots? https://teybannerman.github.io/strategy/2026/03/31/how-many-...
-
comment
Comment #47649848
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…
-
comment
Comment #47571202
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 e…
-
comment
Comment #47561340
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 conce…
-
comment
Comment #47504549
Do you run security review by agents over this?