News for hackers. Stuff that matters.

Abimelex

Well it "works" only because LLMs have the context baked in. The problem is, that this context is something like world-knowledge. Defining the context you need for your exact problem, e.g. your company, will add so much more information that programming is probably the better way.
A 100%! Just imagine you could describe every solution to a problem just using language! Of cause you would to make sure to avoid ANY missunderstanding, but therfore you could invent a language specified for avoiding ambiguity. I could imagine just to reduce the words to a very small corpus so everybody can remember it and have a very strict grammar so a program can effortlessly check correctness of its sentences.
Re:Nitter has more working instances than before the takedowns on Saturday September 05, 2026 @10:07AM (#49576660)
Freedom of speech as long as it fit's in Elmos narrative. It's bit naive to think twitter offers this.
Re:Nitter has more working instances than before the takedowns on Saturday September 05, 2026 @07:12AM (#49575411)
Hot take: All those instances keep the service relevant giving it more reach than necessary. Just shut it down. Cancel Twitter and jump on the BlueSkye or Mastodon train.
Re:Cursor launches Origin, GitHub alternative on Wednesday August 19, 2026 @03:50PM (#49366327)
It doesn't even swallow an entire code base so there is absolutely no need to see the entire codebase. Usually models search in the codebase locally and then use only the relevant parts. There is almost never the whole context just spammed by an entire code base.
it's less more around 94k - IMHO the overhead is the bureaucracy that basically forces you to employ a large amount of non-productive workforce in larger companies just for compliance topics.
also the raised energy prices are fake news regarding indutrial prices, which are differently taxed in Germany than consumer prices. https://www.smard.de/page/en/topic-article/5892/216044/indus...
Gas became expensive, energy for private houeholds became expensive, despite that electric energy for industries is currently on the same level as 2020. Even though there was a short spike in 2022. See: https://www.smard.de/page/en/topic-article/5892/216044/indus...
Re:Australia is offering free daytime electricity on Tuesday July 14, 2026 @09:13AM (#48906352)
That sounds great at first, but just imaging having dynamic price contracts, like tibber, that also forward you the negative prices while still maintaining very low grid fees.
Re:Can you see three trees? on Saturday June 20, 2026 @05:26AM (#48607751)
> People who can see at least three trees from their window have better mental health than those who can't. It seems like the easiest of the three goals to achieve

Here we go, correlation does not equal causation. Simple as that. Planting 3 trees will not give you a better mental health nor will planting 10 trees. But moving in to an environment where many trees grow in front of your window will probably change a lot more than just putting trees in your view.

Thats a literary style called anaphora. Some people learned this in school, so they can use it to emphasize something. IMHO this is not a strong sign of AI, in fact I think this text has no strong AI indicators.
Re:GitLab Down? on Thursday June 11, 2026 @03:09AM (#48487247)
It seems gitlab is down and responds with 503 Error despite the status page shows all green.
Re:Ask HN: Why is the HN crowd so anti-AI? on Saturday June 06, 2026 @03:57AM (#48422539)
Saying "code is just a means to an end" is like saying a Car is just a Vehicle to get from A to B. Which is true to a certain amount of people, but certainly not to people who need a special car like a truck and certainly not to the people who build cars. Developers are car builders.
Re:Is my blue your blue? on Tuesday April 28, 2026 @03:54AM (#47931606)
There are no "cyan-receptors" on your retina so it's not a cultural thing, it's a bio-physics one. Plus as many mentioned the calibration of you display has propably a way higher impact on this than anything else.

So don't be upset, it's just for fun :)

Re:Darkbloom – Private inference on idle Macs on Sunday April 26, 2026 @05:48AM (#47908903)
Any news after 10 days here? Did anyone successfully tried either side of this?
Re:Ex-Tech –> Homeless in SF on Sunday February 15, 2026 @03:47AM (#47022097)
What I probably never get: When somebody is capable and reasonable but jobless, why stay homeless in a city with one of the highest rents? Why not move to a cheaper place, get any job, even a bad paid job will pay a nice flat in a small town. It's always those large very expensive cities that have a huge amount of homelessness.

Don't get me wrong, I do not want to play clever here, it's just a honest question.

awesome and thank you for open sourcing it! Maybe consider renaming it, since there is CraftNote, an app with similar scope in construction business.
Re:Things that aren't doing the thing on Sunday November 16, 2025 @04:13AM (#45943742)
Did I just get trolled on HN? Reading the thing wasn't doing anything.
Re:I almost got hacked by a 'job interview' on Wednesday October 15, 2025 @06:39PM (#45599184)
I had a similar experience and I wonder why bitbucket is alway the choice to host this malware. I files some requests to take that down, but never got a response.
Re:I used to know how to write in Japanese on Friday August 15, 2025 @11:36AM (#44913693)
when I learned Japanese in university I learned writing with the exact method by James W. Heisig. So I didn't used Japanese for about 20 Years since, I forgot almost everything I learned, except the Kanji. I can still remember most of them. It's crazy!
That said, I think there is this thing in between of developing LLMs and using LLMs via APIs and the lines are of cause blurry: Training LLMs (or other neural networks). So best I think is to start digging on the surface and going deeper as long as you feel comfortable. Maybe at a certain point you will have the wish for more power full hardware. Thats the point where you need to decide how much to get invested or to rent a cluster.
Re:Tornado warnings delayed because of DOGE cuts on Sunday May 18, 2025 @05:09AM (#44020031)
That's mostly the thing with safety measurements. If they are there you do not recognize them and if they are missing and something happens it's hard to proof if it would have changed anything.

Have a look on "Heuristics That Almost Always Work" https://www.astralcodexten.com/p/heuristics-that-almost-alwa...

that's not necessarely the weapon LRAD, Long Range Acoustic Devices may also be used for communication. I would be really alerted if this kind of weapon would be used in Germany.

> In the first half of 2020, Bad Homburg's fire brigade and city police used an LRAD 100X system more than 60 times to deliver COVID-19 information.

LRAD 100X: https://danimex.com/products?ProductID=PROD1666

trust me, this is absolutely NOT about liking local manufacturers ...
Re:Start a Computer Club in the Place That You Live on Saturday February 22, 2025 @09:50AM (#43139376)
I am very glad that we have Chaos Computer Club in Germany. It's by far more than just a time and place where nerds meetup to do computer, they are already some kind of institution, they have a voice in politics and often requested for independent consulting. But "doing computer" is how it all started.
Re:Show HN: ESP32 RC Cars on Sunday February 02, 2025 @06:15AM (#42907927)
FPV car racing incoming!

Older »