Hacker Newsnew | past | comments | ask | show | jobs | submit | whirlwin's commentslogin

Norway hosts the yearly national AI championship for the second year in a row. Team registration page is open.

Anyone got experience with Claude Code gateways?

https://code.claude.com/docs/en/gateways

Seems like a good way to govern usage to an alternate model provider


Having worked with cloud for almost 2 decades. The term self-hosted is indeed what you describe. The opposite is "managed services", e.g. services that are packaged by the vendor without the need to manage auxiliary needs like CPU, memory, disk, log rotation, etc.



Can someone explain why this is a agent skill and not just agent config (AGENTS.md / CLAUDE.md)?


Skills are kind of a new thing starting around January 2026, but the spec was established about 12 months ago.

https://news.ycombinator.com/item?id=46871173

Anyways the most layman way I’ve seen it explained is this: skills help save token usage for the right context. Not every request needs all instructions all the time - running tests is different than reviewing a PR, so why should the context window have instructions for both on every request?

So now you split instructions into “skill” files, which are basically opinionated markdown files. And you invoke those with something like /grill-me in the prompt depending on what you’re doing.

There are some steps to have the agent automatically know what to invoke for you but in my experience this automation is hit or miss.

It is also challenging to keep track of a growing library of skills and keeping those up to date.

So YMMV regarding skills. I typically keep things in a single markdown file even if the context window gets a bit bloated.


Yeah, I get that. I have created dozens of skills, but they are usually to accomplish very specific tasks. Some of them have accompanying scripts, etc.

My point is that this sounds more like a general AGENTS.md use case, similar to defining tone of voice, output format, etc.

It just seems skills is the only way to distribute certain "behavior" as of today. But not everything is a skill IMHO, and not this is not one of them.

On the other hand, maybe we're seeing an evolution of what skills are becoming.


Thank you very much, that was so easy to understand, it'll genuinely help me.

Thanks again.


You can /i-have-adhd when you get a wall of text and are exasperated. You don't always want the responses that it generates when you /i-have-adhd, and things in AGENTS.md tend to lose weight as context grows.


It's a fashion choice.


Because it’s wrong, and you are right. It should be in your global AND per-project md’s… Perhaps in a custom output style too.


It lets the author pretend to be doing software engineering, like running tests and deploying versions.


Timeline: - Aug. 7 GitHub introduces configurable GH Copilot effort levels - Aug. x GitHub executives identify a great opportunity related to the early August change - Aug 28. Default GH Copilot review is now "Balanced" effort level


This brings back memories!


IKEA is the new "fast fashion", but for furniture.

You buy something one day, and it starts to deteriorate and become janky after a year, and you'll have a buy a new one. All products have gone through spreadsheet cost optimizations.

It wasn't always like that. If you're lucky to get your hands on an old IKEA bookshelf (Billy), it's sturdy and will last forever.


We’ve had IKEA furniture for over 15 years, sometimes storing it in the attic for a few years after disassembling it, then assembling it again. We’ve also kept the main bodies of our living room furniture while replacing the doors. We sold the old doors on eBay, and other people reused them.

I also inherited some “regular” living room furniture after my mom passed away. It cost about four times as much as IKEA’s higher-end lines. After moving it from my mom’s place to my office, I can already see it falling apart after just three years (total lifetime as my mom only had it for two). The quality is so shite that I honestly wish my mom had bought IKEA.

In the future, I’ll either buy custom pieces from a furniture maker or choose IKEA's higher end lines for longevity and reusability.


I have no experience with newer IKEA furniture, as my old IKEA furniture seems to last forever.


They make stuff at all price points. The basic stuff is sturdy paper meant to last a few years, something like Ivar is solid (ish) wood and will outlive you.


> You buy something one day, and it starts to deteriorate and become janky after a year, and you'll have a buy a new one

I had a LACK table (9.99 euros at time of acquisition) last for 10 years before a move forced me to give it away. I also have a few random things from them (wooden cutting board, grater, I think a bookshelf) and everything is pretty OK, even the cheap stuff.


A lot of people want this to be true, but alas it isn't. The stuff lasts. Probably for a simple reason: Any given product line is bought by millions of customers, so design flaws are quickly found and remedied. I see it as a form of safety in numbers.


Even the stuff they've traditionally been good at?

Funny thing is, I haven't bought much furniture for ages since my old IKEA stuff has lasted for several decades and is still going strong. Their major kitchen appliances are crap, though.


we miss it dearly in Russia. most (reasonably-priced) furniture we had before Ikea was worse, and what we have now is worse still.

high quality furniture loses most of its value the moment it becomes preowned, so it only makes sense to buy if you are absolutely certain you aren't going to move anytime soon, which is not realistic for most people. Ikea is just good enough.


That's a good way to kill off motivated employees.

"We don't know why we're doing it - it's just mandatory".


Only if you write a bad policy, so don't do that.

The better way is that for each policy you look at what do you actually want to do and how you want to do it, and then write that down as the policy. Now the policy makes sense because it's how you wanted to do it anyway.

I've set up policies and processes from the ground up for SOC2 audits in startups, that's how I do it.


Great, so stepping into any organization green where the subvert command is to be unwilling to update policy will enable this.


Smart employees totally understand: "we do it because it makes it easier to explain to auditors, customers, new employees, non technical managers".


No, cogs understand that. Smart employees want to update policies to be an effective mandate versus lip service to the C-suites asshole


The policy can be changed.


Unless you’re every company I’ve worked st over the past 20 years.


Does there exist any tool to analyze PR feedback quality and usefulness?

I've been trying to explain to compliance employees that if the majority of PR reviews anyway is just "LGTM - Just merge" (I don't care), what's the actual value of PRs? It's just facade.

On a different note, we're looking into artifact attestations and admissions through Sigstore, which is solves many of the same challenges but through different means.


Consider applying for YC's Winter 2027 batch! Applications are open till November 2.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: