News for hackers. Stuff that matters.

draxil

Re:LLMs reward expertise on Tuesday August 04, 2026 @02:05AM (#49164814)
> my friend is a novice and needs extra help with things like: copy pasting the code into a text file

I don't think this is using an agent harness.

Re:Mozilla: The state of open source AI on Friday July 17, 2026 @12:18PM (#48949121)
Almost all about open weight, but the title says Open Source.
rip off.
Re:The Emacsification of Software on Thursday May 14, 2026 @04:36AM (#48132655)
Google wave rides again!

I'd say the thing with email that most improvements would need improved standards?

That said, as with the emacs user example, the ability to automatically process all your email in madly custom ways can now be opened to the masses.

Except it's often faster to make the change yourself than explain it to an AI.
Re:Grok 4.3 on Friday May 01, 2026 @06:51AM (#47973244)
I don't like that word, which was previously a common part of my vocabulary, being forever ruined?
Re:I Quit. The Clankers Won on Wednesday April 01, 2026 @09:34AM (#47600654)
I think the fact you need tool calling to stop it doing that, shows the underlying issue with trusting it to do anything without a human
Re:I Quit. The Clankers Won on Wednesday April 01, 2026 @09:32AM (#47600629)
Useful tool, and if you're just scratching a small itch it's great.

For any serious system you still need to understand and guide the code, and unless you do some of the coding.. You won't. It's just novelty right now is skewing our reasoning.

Re:I Quit. The Clankers Won on Wednesday April 01, 2026 @09:29AM (#47600594)
This is a good parallel. In the 90s when I learned to drive I was quite good at navigating. Now google maps is on a screen in my car telling me where to go whenever I drive beyond my most common routes.

Really all the research telling us about AI skills atrophy.. We should have guessed from previous experience.

Good to have more than a hammer in your toolbox!
Re:iPhone 17 Pro Demonstrated Running a 400B LLM on Tuesday March 24, 2026 @05:12AM (#47500179)
I assume you mean open weight models? I wish we had better open source models. It would make LLMs far less icky if we had nice clean open trained models. A breakthrough on the cost of training would be nice.
Re:The “small web” is bigger than you might think on Tuesday March 17, 2026 @04:59AM (#47410140)
I think Gemini might be wise to rename, now there's a commercial product trampling all over it's namespace.
emacs users who are hostile to you configuring things, aren't really getting the point IMO :)
how many of these stars were applied by openclaw?
Re:Redefining Go Functions on Tuesday February 10, 2026 @04:55PM (#46967482)
Spirit of Perl is still alive
Re:Testing Ads in ChatGPT on Monday February 09, 2026 @02:31PM (#46949856)
We've seen this process before. If you don't pay, you are the product.
Well especially the lisp parts!
Sort of except it seems the more the co-worker does the job it atrophies my ability to understand.. So soon we'll all be that annoyingly ignorant manager saying, "I don't know, I want the button to be bigger". Yay?
This to me is the point.. LLMs can't be responsible for things. It sits with a human.
Re:Vibe Coding Kills Open Source on Monday January 26, 2026 @09:14AM (#46765856)
I think that's an optimistic interpretation of how good LLMs are?

But I think the reality is: LLMs democratise access to coding. In a way this decreases the market for complete solutions, but massively increases the audience for building blocks.

I was just about to post that it didn't affect us (heavy AWS users, in eu-west-1). Buut, I stopped myself because that was just massively tempting fate :)
Re:Claude Sonnet 4 now supports 1M tokens of context on Tuesday August 12, 2025 @03:57PM (#44881149)
But it's pretty much a given at this point that if you use agents to code for any length of time it starts to atrophy your ability to understand what's going on. So, yeah. it's a bit of a devils chalice.
Re:The Q Programming Language on Thursday August 07, 2025 @05:02PM (#44830322)
does quickly draw attention to it's examples directory though
Re:Claude Code weekly rate limits on Monday July 28, 2025 @04:43PM (#44715376)
Of course ripgrep runs on your machine and you control it.
Re:Grok3 Launch on Tuesday February 18, 2025 @10:07AM (#43090332)
Yes, but then they also redefined what that means half way through.
I can't get past someone not being allowed to turn on bluetooth!
Re:1M Users on Monday September 02, 2024 @04:29AM (#41423624)
Some people (like me) have a fixed IP for their internet connection. Although this isn't super common any more.
Re:Threads Enables Fediverse Replies on Thursday August 29, 2024 @09:50AM (#41390817)
OFC most of the fediverse has blocked threads already.
I assume in this case you point at the idiot who said this was a good idea?
Re:Show HN: Anycast+ – An AI-powered podcast app on Monday August 12, 2024 @04:25AM (#41222328)
Well killer of podcasts at least.

Older »