Hacker Newsnew | past | comments | ask | show | jobs | submit | dncornholio's commentslogin

Terrible. You cannot 'ls' if ls is not the right answer. Completely useless.

That's not true. You can absolutely use ls and other commands to poke around before creating the winning command.

They can. They don't want to though.

How does Kagi know what is AI stuff? I don't see how they can 'just turn it off'

By "turn it off" I mostly mean that Kagi have their own AI driven tools available, but a toggle in your user settings disables it completely.

ie it's not forced down your throat, nor mysteriously/accidentally/etc turned back on occasionally



so it is like humans vs robots started? robots ask humans questions to verify they are not robots. humans mark content as robot-generated to filter it out.

My first instinct is that users abuse it like they do any other report/downvote mechanism. They see something they just don't plain like, they report it as AI slop.

It will also let the LLM process even more tokens, thus decreasing it's accuracy

Because it's stateless it's not pointless? Good codebases don't change fast. Stuff gets added but for the most stuff, they shouldn't change.

A well-documented codebase lets both developers and agentic models locate relevant code easily. If you treat the model like a teammate, extra docs for LLMs are unnecessary. IMHO. In frontend work, code moves quickly.

We shouldn't rely on YouTube to write our history. It's just an American entertainment website that makes money of ads. It has no other obligations. It can do whatever it wants, or what the US government wants. This is not news.


Is this even a fair comparison when Ford and Chrysler offer a lot more models than Tesla does?


Fords recall numbers have skyrocketed in recent years. So Fords real comparison to its previous self, 2015 they had 68. Why isn’t Fords roughly doubling of recalls news?


It's reasonably well known that Ford has had a very bad year for recalls; it's definitely made the rounds in the auto world, and breaks through to the mainstream news from time to time.

https://www.motortrend.com/news/2024-2026-ford-ranger-recall...

https://247wallst.com/investing/2025/10/17/ford-recall-recor...

https://www.usatoday.com/story/cars/recalls/2025/09/24/ford-...

https://www.macheforum.com/site/threads/ford-issues-more-saf...


>Why isn’t Fords roughly doubling of recalls news?

Oh, I don't know, maybe because Tesla is bigger than the rest of the entire industry combined?

Besides, safety recalls are what matters. I get lots of small qualtiy-related recalls that are so minor I don't even bother getting them done. Meanwhile, Tesla does what it can to avoid quality recalls, because for a while it was a marketing blurb for them.


By units sold per year Tesla is the 15th biggest car company. Ford is 6th. (This is with Hyundai and Kia counted as the same).

By revenue from those sales rather than units, Tesla is 12th. Ford is 6th.


It’s not. For example, Saab has had 0 recalls.


Saab also currently produces 0 models.


That’s the point.


There was a time where the world just trusted the US blindly. This is sadly not the case anymore.


Not using Google but instead use a Mullvad or Brave search engine isn't solving any problem. Because if you cannot trust company A, you also shouldn't trust company B.

If you want real and total anonymous search, use a public computer.


Public wifi on burner phone.


Even then some criminals actually log-in to google or other accounts on the burner. :facepalm:


That's actually a very specific domain, which is well documented and researched in which LLM's will alawys do well. Shit will hit the fans quickly when you're going to do integration where it won't have a specific problem domain.


Yep - visualizing clustering algorithms is just the "CRUD app" of a different speciality.

One rule of thumb I use, is if you could expect to find a student on a college campus to do a task for you, an LLM will probably be able to do a decent job. My thinking is because we have a lot of teaching resources available for how to do that task, which the training has of course ingested.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: