Viewing profile — d0mine
d0mine
HN member- Joined
- Fri, Jun 06, 2008, 3:25 AM UTC
- HN karma
- 4,732
- Public activity
- 2,474 items
- HN profile
- View on Hacker News ↗
About d0mine
Recent public activity
-
comment
Comment #49225852
LLMs can write TLA+ models just fine. It can help even with small mobile apps. Surprisingly, simple TLA models were able to find design/workflow issues almost in every of a few vib…
-
comment
Comment #49203317
it reminds me that making a ring is not rocket science https://youtube.com/shorts/NPKOGqXKLq4
-
comment
Comment #49143223
Wait until it becomes popular.
-
comment
Comment #49135946
"Садись, два» is more idiomatic
-
comment
Comment #49121418
Isn’t it exactly the opposite: Bun overused LLMs -> codebase became a mess hard for humans to reason about. Luckily, bigger smarter model still could handle the mess and AI lab can…
-
comment
Comment #49115824
The error grows exponentially. For example, for equal-mass triple with Earth sized orbit initially, the prediction limit is just a few hundreds years even if you know initial condi…
-
comment
Comment #49115358
Models have to lie otherwise they won’t be “aligned” The reality itself may not be aligned with model creators.
-
comment
Comment #49069531
"centering div" is a classic problem (/trauma/meme) that sounds trivial but had no universal solution (until 2017?).
-
comment
Comment #49046064
How about total surveillance total thought control total power in a hands of few trillionaires in the near future. Drones killing undesirables with cheering crowds watching. It is …
-
comment
Comment #48899829
These are orthogonal: - there are people who do not want LLM contributions being accepted into emacs itself (legal, maintainers burnout, etc reasons) - there are projects (such as …
-
comment
Comment #48700139
How many accounts Anthropic used to mine the web
-
comment
Comment #48607745
It is more like an ability to recognize the word when it is used in context. I got ~1/3 that is very generous estimate even for "recall" case (recognize), and it obviously false fo…
-
comment
Comment #48590949
Mimocode(opencode), Pi Coding Agent
-
comment
Comment #48433599
It is how these agencies operate. They mask malevolent activity behind good front (“think of the children“, “age verification“ -> censorship/total surveillance. Medical aid -> over…
-
comment
Comment #48433474
As I understand RL makes foundation models stupider ( less capable , not more) but better at following instructions.
-
comment
Comment #48427239
U.S. Military Turned GPS into a Global "Numbers Station" https://news.ycombinator.com/item?id=48414479
-
comment
Comment #48414758
In practice, when conventional commits are used with git emojis, they look like “scope: what is done” already (“ scope: …”)
-
comment
Comment #48414639
Conventional commits (especially with git emojis) show at a glance the blast radius of the change (eg whether it breaks the product itself or just some internal dev tools). Emojis …
- story
-
comment
Comment #48332291
If you need a network boundary, what MCP provides that REST API + llms.txt can't do?
-
comment
Comment #48331183
In practice, you would use an already written implementation, maintained by somebody else. An option that is often ignored by LLM (copy-paste galore). For example, imagine if textu…
-
comment
Comment #48284399
Almost everything you see on the topic is propaganda. Alternative views are suppressed (though I’m surprised on the relative diversity I’m seeing in this thread)
-
comment
Comment #48183425
“Either or” is too extreme. Both can be true at the same time even if at different levels of abstraction eg a table and atoms it consists of may exist at the same time. Depending o…
-
comment
Comment #48127814
“Those who say they lack time to build tools are precisely the ones who cannot afford not to.”
-
comment
Comment #47996136
Unlike Kindle, Amazon can’t shutdown your bookshelf