News for hackers. Stuff that matters.

cracell

Re:Why do LLM pelicans look like this? on Wednesday October 14, 2026 @01:33PM (#50091572)
This a huge feature for coding.

I don’t want creative code. I want boring code following generally agreed upon best practices.

If you need more creativity it can come from the user or the harness.

Re:Why aren't AI companies being charged for hacking? on Monday October 12, 2026 @11:09AM (#50057562)
Are any victims calling for prosecution?

It’d be a waste of tax payer money. The companies who were hacked are just directly receiving restitution behind closed doors. Unless they are unhappy there’s no reason to bring the courts into it.

I completely agree that proper safeguards were not in place. But response is happening just not in public. Companies work problems out between their own lawyers all the time because it’s much cheaper, faster and easier to control the PR around.

Re:Grieving the Loss of Details on Saturday October 10, 2026 @09:41PM (#50038995)
What LLMs are you using? Just simply telling Sol 6.1, Opus 5.5, Fable or Astra to performance test something will get you a solid improvement in poorly optimized code.

Giving it a specific plan will get you a solid test harness.

And setting up an autoresearch system and running it overnight will get you expert level optimizations if you set the metric up right.

These things excel at performance optimizations.

Re:Agents don't need memory. They need documentation on Sunday October 04, 2026 @11:11AM (#49954580)
Yeah… this makes good points about why memory systems don’t work. Then tells you the solution is… a memory system.
Re:Ask HN: Anyone still coding like 2021? Where do you work? on Wednesday September 09, 2026 @10:19AM (#49627055)
Regardless of if a new tool is useful or not, if it’s being pushed internally then embrace it.

If it’s not useful now you have authority on why. And if it’s not is useful then you are better at your job.

More the second.

For programmers this is the equivalent of when accountants got spreadsheets. We can just tell the machine what to do without manually performing all the steps.

Some programmers enjoyed the code writing more than the problem solving though.

Export controls have highly motivated China to figure out how to make state of the art chips entirely in country.

It’ll certainly take years but I would not bet against China’s ability to manufacture something.

You must have different use cases than me.

I find even Deepseek Flash v4 0731 even outperforms Opus for me (at 10x the speed two).

Using Sol, Fable, Kimi 3 and other recent models has been unbelievable for me. I didn’t think we’d get to this level for years.

I’m using them for Ruby, TypeScript and Python. In large existing codebases but also lots of tiny tools.

Re:The AI bubble is popping; we just don't know it yet on Monday August 03, 2026 @08:43AM (#49155007)
I don't understand this argument.

Go to OpenRouter and look at all of the unsubsidized providers.

Re:What AI coding costs you on Saturday February 28, 2026 @10:42AM (#47196624)
> micro-agression against readers
Re:What AI coding costs you on Saturday February 28, 2026 @10:40AM (#47196600)
This was my biggest frustration with LLM based coding but Agent Skills have largely solved it.

While there’s a lot of room to improve them it’s a huge game changer for effectively coding harnesses.

Re:What AI coding costs you on Saturday February 28, 2026 @10:36AM (#47196550)
This is actually a big advantage of using AI.

Using simple mature tech stacks following best practices makes your product much better.

Developers have a strong desire to reinvent the wheel and it wastes so much time.

Innovative should only be attempted in your product domain if you are trying to make a successful company.

Re:Experts Have World Models. LLMs Have Word Models on Sunday February 08, 2026 @02:44PM (#46937786)
I found it to be an interesting angle but thought it was odd that a key point is is "LLMs dominate chess-like domains" while LLMs are not great at chess https://dev.to/maximsaplin/can-llms-play-chess-ive-tested-13...
Re:Tell HN: Recruiters are lying about remote positions on Thursday April 07, 2022 @02:33PM (#30948559)
Was this not at-will employment?

While getting it in writing is good, it doesn't actually protect you. Vast majority of people are working at-will. Which means either party can change the terms of employment whenever. And if the other party disagrees then employment is terminated.

In this case meaning, if your contract says remote then they can change it to not remote at any time. That said, any company that will pull shenanigans like that you don't want to be working for anyhow as they don't respect you and that will impact you across all aspects of your work.

Re:The return of the 10-minute eviction on Monday December 20, 2021 @11:03AM (#29626366)
What sort of legislative changes would you like to see to address this?
"Salesman says product he's selling is great!"
Re:Open letter from the BMJ to Mark Zuckerberg on Friday December 17, 2021 @02:56PM (#29597570)
I would strongly argue that coordinated censorship of media should be illegal.

It's not today. But is it in society's interest that a small group of elites gets to decide what we can discuss on our primary discussion platforms?

Re:Open letter from the BMJ to Mark Zuckerberg on Friday December 17, 2021 @02:55PM (#29597542)
Fact checking is just censorship. It's literally a group that gets to decide what is an acceptable view and what isn't. How is that not just plain censorship?

You can certainly argue that censorship isn't always a bad thing. But calling censorship "fact checking" is purposely misleading.

Re:Why Zulip will stand the test of time on Friday December 17, 2021 @02:45PM (#29597414)
XMPP supports extensions.

Generally speaking, use the standard until you can't. Then just extend it and write up a proposal for your extension to make it into the next version of the official protocol.

Re:Why Zulip will stand the test of time on Friday December 17, 2021 @02:43PM (#29597389)
I have no idea how Slack threads are intended to be used. Their own examples are very trivial and the implementation feels like like a first pass that they never did any usability testing with.
Re:SolidLight offers a true holographic video display on Friday December 17, 2021 @12:01PM (#29594909)
This is obviously a lie as in their own demo video it's very clearly not a physical chameleon.

Remember articles like this are PR pieces. Specifically written to sell the product and find more investors in the company.

Food studies are always all over the place.

The only real consistency is that eating loads of processed food (think chips/soda) is strongly correlated with health issues.

Re:Don't start with microservices – monoliths are your friend on Thursday December 16, 2021 @02:31PM (#29582692)
Simple rule of thumb is one backend per team.

Things like upgrading the language version should not require coordination between multiple dev teams.

Of course there's 100s of permutations that work. Optimize for your situation. And if you have no clue what the right call is, go as simple as possible until it breaks on you.

Re:From Node to Ruby on Rails on Thursday December 16, 2021 @11:27AM (#29579960)
I wouldn't say that.

My team uses a Rails backend and React apps on top. For us, React apps compared to Rails views just about cut our feature delivery time in half.

Of course, it depends on what domain you are working in. Dynamic frontends on Rails are a pain compared to React and probably some other front-end JS.

That said, on the backend Rails is a very mature framework that is hard to beat on most things.

Re:Lego Rolls Out a Collection of Wooden Home Accessories on Sunday December 05, 2021 @12:17PM (#29450837)
I don't think they will.

I saw a bunch of this collection at Target and it all looks terrible in person.

To me Lego as a brand is quality and creative. Whereas these products all felt cheap and janky.

I would bet on them all being on clearance after Christmas.

Re:There may be a steep privacy cost if you park here on Sunday November 14, 2021 @04:30PM (#29220921)
I would be very surprised if Trader Joe's lease didn't include parking conditions for exactly this reason.

Bad parking kills many businesses.

Re:I read a book that blew my mind a little on Sunday November 07, 2021 @07:34PM (#29145015)
No, no. It's this new thing I invented.
Re:Combating disinformation with humility on Thursday November 04, 2021 @09:29PM (#29114496)
I think we need to find a better way for the philosophy behind the scientific method to click.

The entire idea of a "fact" is flawed. We simply have more good evidence for some things than others. Teaching people to critically evaluate and compare the evidence is the trick.

Perhaps studying different perspectives of a politically neutral historic event would help people to understand.

Re:Internet Hay Exchange on Saturday October 30, 2021 @01:07PM (#29050370)
Is this because middlemen take too big of a cut?

I work for an agricultural company that does a decent amount of hay sales as a middle man but I'm not too familiar with that part of the business.

So?

The solution to discrimination based on race is certainly not to discriminate based on race.

Why do you think more racism is the solution?

Older »