News for hackers. Stuff that matters.

4b11b4

Re:Ask HN: Are you tired too in this AI era? on Friday October 30, 2026 @11:45AM (#50305587)
Yes, but periodic audits.
Re:Why are good developers so wary of agentic development? on Thursday October 29, 2026 @01:37PM (#50292956)
I'd lean similarly, but those regimes you list aren't likely going to be done by accident.
Re:Why are good developers so wary of agentic development? on Thursday October 29, 2026 @01:33PM (#50292878)
Putting pair programming and TDD in the same box as agentic development (with, as you assume, zero review of the code) seems...
Re:Bernstein – open-source governance layer for AI agents on Thursday October 29, 2026 @03:11AM (#50285463)
How can people even...
Re:Start Doing Graph Theory on Wednesday October 28, 2026 @11:26AM (#50275279)
I have just taken this in stride but it has struck me a few times recently that everything I see now.. I basically have to classify it as to be immediately discarded or worth my time to even begin reading, and even if I do continue reading then I still have to be constantly evaluating if a person bothered to struggle with (write) it or not.

Quite frankly this is.. fucking terrible? Even worse, the end of something for humanity..?

There's a dedicated furry toggle? I mean... I've heard of this but, now I feel like I really missed some societal shift in the world.
This reads as some people made up some categories then classified people into them.
FWIW me too now, but because of my old dog. Also I'm possibly about to sign for the guard, so I guess I'll be ok with that 4am wake up.
wait over a year?

What were the design decisions which you have settled on and what did you throw out?

Re:No Signs of AI Payoff Outside the Tech Sector on Saturday October 24, 2026 @04:48PM (#50225096)
No, we know that when technology (particularly: Internet connected laptops) is introduced into classrooms competency declines. This has been shown to be true internationally
Re:Using LLM for confidence scoring is a bad idea on Wednesday October 21, 2026 @11:37PM (#50190906)
The first half of your first sentence is correct
Re:Using LLM for confidence scoring is a bad idea on Wednesday October 21, 2026 @11:19PM (#50190758)
Yeah, using them for any (most) subjective task is generally incorrect
Re:The Future of CSS on Wednesday October 21, 2026 @02:52AM (#50176982)
Probably. Trade-offs is engineering
Re:The Future of CSS on Wednesday October 21, 2026 @02:48AM (#50176955)
Ignorance and generally a hater position
Re:The Future of CSS on Wednesday October 21, 2026 @02:20AM (#50176749)
Good to see Josh writing, especially after his courses have taken such a hit. He is excellent. As an electrical engineer and also now CS grad and someone who has purchased his courses wanting to be able to work across the entire stack.. yet have also thought "thank god I don't really have to learn css" now (yes, due to increasing model performance).

On that note I may know just enough to be dangerous thanks to Josh (casting spells: e.g. shouldn't we group those in their own container and then within that container shouldn't that be a flex box?). I guess I'm here to say humans are full of contradictions.

Same I just leave 6.1 on Max. Don't touch that dial
Re:Advanced coding in low-resource programming languages on Tuesday October 20, 2026 @02:32PM (#50170637)
That's.. not..
Re:Credit Where Credit Is Due on Tuesday October 20, 2026 @09:30AM (#50166112)
Nevermind! I just went down a rabbit hole on "negative hard feature mining" that has simple origins from early days of object detection and bootstrapping!

I'm sure pangram has to deal with a lot of bullshit to keep retraining on new model output though.

Re:Credit Where Credit Is Due on Tuesday October 20, 2026 @09:03AM (#50165753)
Can someone educate me - does pangram actually work? Why are people acting like this tool is god?

I thought definitively classifying writing was essentially an impossible problem. Of course, we can often smell it, but again, that's not definitive.

Re:Vite+ an excellent toolchain for AI agent development on Tuesday October 20, 2026 @08:07AM (#50165077)
ugh
No.. MCP is for actions
this is just a guard on the function definition?
Re:Open source 160 sound visualization experiments on Wednesday October 07, 2026 @07:19PM (#50000086)
Can you make them all move on repeat for a sine sweep followed by some misc transients
that is a good one re llms
I like this mindset but damn that's a lot of tokens? At what cost? And then to continue to maintain and .. idk.. I suppose it'll work? If the motivation is strong enough and momentum is sustained?
Re:All I wanted was a custom domain email on Sunday October 04, 2026 @07:02PM (#49958849)
Seems you're... conflating the concepts of spamming people with using a language model to generate code
Re:Blogging with Gleam, Org-Mode and Pandoc on Friday October 02, 2026 @06:50PM (#49939567)
lol yeah this should just be a pile of elisp
Re:DeepSeek Harness Desktop for macOS and Windows on Friday October 02, 2026 @08:56AM (#49933013)
Run as server, agent can run arbitrary elisp
Re:Turbo Haskell on Friday October 02, 2026 @08:54AM (#49932991)
Sit down
Re:GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price on Tuesday September 29, 2026 @09:50PM (#49903406)
Didn't even bother trying it yet

Older »