News for hackers. Stuff that matters.

vetler

Re:Why MCP Was Always a Bad Idea on Monday September 21, 2026 @07:08AM (#49785686)
Is this another "Dropbox is just rsync"-like post?
> Your one example doesn't make all of LLMs a lie.

It's not a lie though, because the truth isn't guaranteed by the mechanism that generates the answer.

Re:I'm going back to writing code by hand on Monday May 11, 2026 @03:29PM (#48099565)
The wide range of different responses to this post illustrates an important point; we can't agree on how to use LLMs in software development, and are still discovering new things.

And in a couple of months we might be doing things completely differently because of some new model or new framework.

That's really cool.

Re:Ghostty is leaving GitHub on Wednesday April 29, 2026 @04:05AM (#47945422)
Have not had such big outage issues as what's described here, although I have noticed more stability issues lately. Is this worse while Europe is sleeping maybe?
Re: on Monday March 30, 2026 @06:29AM (#47572574)
Came back here to say I was wrong! I have been experimenting, and it is doable. I have been experimenting with setting up a scraping pipeline with LLM enrichment since I wrote the comment above, and have very positive results so far. :)
Re:Coding Agents Could Make Free Software Matter Again on Monday March 30, 2026 @06:26AM (#47572551)
But LLMs themselves are literally not going away, I think that's the point. Once a model is trained and let out into the open for free download, it's there, and can be used by anyone - and it's only going to get cheaper and easier.
Re: on Thursday March 26, 2026 @07:54AM (#47529355)
You will absolutely struggle to get all the info you need into 700 tokens per page.

Edit: There's also the added complexity of running a browser against 1M pages, or more.

Re: on Thursday March 26, 2026 @05:11AM (#47528197)
My instinct was also to use LLMs for this, but it was way to slow and still expensive if you want to scrape millions of pages.
As a Norwegian, yeah you're not wrong. We have a lot of challenges to overcome as the oil age is coming to an inevitable end, although there are many here tho refuse to see the writing on the wall.
Re:Amazon in advanced talks to buy Zoox on Wednesday May 27, 2020 @08:42AM (#23322299)
Their YouTube videos are just amazing to watch: https://www.youtube.com/channel/UCh5q-FtihPqzTbgEkZQRy3g
Re:Tesla Software Version 10.0 on Friday September 27, 2019 @06:11AM (#21090221)
I used to be "anti Tesla", then I tried one, and now I own one.

Teslas are disruptive - they're not what you expect of cars. I will never look the same at a car again. Tell this to anyone who doesn't understand, and they simply won't understand what you're going on about.

Over a year in; driving my Model X still makes me smile.

Re:WiFi Hides Inside a USB Cable on Wednesday February 20, 2019 @07:24AM (#19207306)
Would be even scarier with eSIM, but I suppose it's just a matter of time before we get that.
So no one opened up one of these and looked at the components?
Re:Decision On Bitcoin ETF Coming March 11 on Thursday February 02, 2017 @05:49AM (#13549600)
On a related note, there's already a Bitcoin ETF on the Swedish stock exchange: http://xbtprovider.com/
Re:Should I Comment My Code? The Case Against Code Comments on Thursday October 06, 2016 @08:50AM (#12651957)
How to create readable code that explains itself should have more focus. It's not just about naming classes, methods and variables, but also about structuring your code. It's quite possible to create a method with the perfect name that is over nine thousand lines long and difficult to understand.

This can be very subjective, but code complexity metrics can help identify problem areas. I find that areas with high complexity often benefit from refactoring into smaller pieces making it more readable and self explanatory.

If you can't structure your code to explain itself, perhaps commenting isn't such a bad idea, at least it would be a record of your thoughts at the time, until someone else comes a long and hopefully cleans it up.

> Not sure why one would want to attack that.

Well, that would make it less obvious.

1. Take a short-position on Delta on the stock exchange

2. Sabotage a piece of infrastructure that's important to operations

3. ???

4. Profit!

:)

Re:Vivaldi 1.2 release on Friday June 03, 2016 @07:24AM (#11829636)
> Okay, I have to question this. Why is a browser vendor spending precious time and money adding a mailbox to their browser?

Because Jon von Tetzchner (founder of Opera and Vivaldi) thinks having it in the browser is superior to having it as a separate app. It used to be like this in Opera as well. His goal is to provide an application with more value than just the stripped down browsers you see these days.

> I always wondered why, for the longest time, they thought competing with Chrome and Firefox was a good idea

Because Jon von Tetzschner was and is passionate about building a good browser, and didn't really care that the odds were (are?) against him.

But when Opera is brought up, the focus is always on the Desktop browser. However, the money was always in devices - Opera has traditionally been really big on a plethora of devices.

Also, Opera both on desktop and mobile, has long been big in markets other than the US, especially eastern Europe.

What was the turning point when cops became the bad guys in the US?
From experience, it's amazingly easy to break something unintentionally when you're making changes, and even with a relatively small codebase it quickly becomes difficult to keep everything in your head.

I'm not an advocate of TDD though, and I agree that more effort should be put into how to test.

Somewhere, this software sits in a source code repository. Someone planned it, wrote it, reviewed it and approved it. Where are these people, and why are they not speaking up? Why have there not been any whistleblowing on this, it's huge?!
Re:Safe from what? on Thursday September 03, 2015 @04:18AM (#10163823)
"Parents install a baby monitor. You won't believe what happens next!"
Re:The Gracie jiu-jitsu story on Thursday August 27, 2015 @04:04AM (#10128145)
Yes, he is mistaken. BJJ is certainly practiced in favelas, and there are people who use it to give youths something to do, as a way to keep them away from crime, drugs, etc.

See the Tererê Kids Project, for instance: http://fightland.vice.com/blog/social-change-through-jiu-jit...

Re:The Gracie jiu-jitsu story on Thursday August 27, 2015 @04:02AM (#10128138)
> broken eye sockets and arms aren't enough to call a fight

There's MMA, and then there's no-holds-barred (or vale tudo, literally "anything goes").

MMA in the western world today is an organized sport, with rules to protect the fighters, and has little to do with how the Gracies used to fight in Brazil. Yes, you can still find nhb events, and you can still find MMA events that are freakshows, but events like UFC, Cage Warriors, Bellator, etc. are very well organized, and fighter safety is important.

Re:Google Launches Sidewalk Labs on Thursday June 11, 2015 @05:21AM (#9698567)
Sounds like a waste of water, though.
Re:No, you're not 'running late', you're rude and selfish on Thursday June 04, 2015 @09:33AM (#9659099)
> terribly antisocial

No... no, it's not. Terribly antisocial would be to have it at lunch time. Let's not make it worse than it is, 9 o'clock can be inconvenient for some, but it's not "terribly antisocial".

Re:No, you're not 'running late', you're rude and selfish on Thursday June 04, 2015 @09:29AM (#9659074)
Obviously, being late in itself does not make you any more or any less successful, so there must be something more to it. If you find being on time is stressful, perhaps it was a good idea to embrace your lateness, though.

Older »