whirlwin

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.

Down again: https://status.x.ai/

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.

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

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.

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

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

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.

So bubblewrap is the community medicine to this issue. But isn't it funny that we're now trusting a single GH user (although allegedly a RH employee) for the supply chain security? Imagine bubblewrap itself being compromised.

Now you trust a single GH user rather than a company. Fair enough. I just think it's very paradoxical.

Does anyone know if it is useful for bidirectional sync between codeberg and GitHub?

In that case it sounds like the last waves of malicious reset attempts happened after the patch was put in place

I got a suspicious password reset request email today from Meta but it landed in my inbox. Luckily I have MFA and after checking audit logs inside IG upon logging in, I did not see anything suspicious.

The RCA and preventive measures was a pleasant read. I got a lot of respect for companies putting a lot of effort into incident reports like these. Makes them appear very professional rather than just blaming the cloud provider outright.

I've started experiencing them first time during Q1 this year up until now. Used to be pretty stable before that.

We just invested a lot migrating 300+ pipelines from Azure DevOps to GitHub Actions. What a bummer timing-wise. Anyone got an alternative to GitHub Actions?

Not long ago RH Product Security created a blog post around lola, their AI context package manager. Ref: https://developers.redhat.com/articles/2026/04/08/manage-ai-...

The article refers to their GH repo and that was all cherry and sunshine up until just recently, where it is redirected to https://github.com/LobsterTrap/lola.

No mention of it anywhere. "Did it get compromised?" was my initial thought. Still in the fog here.

MS is turning focus to compliance market when they cannot compete on agentic tooling capabilities

If you don't have ad-blocker, you will get redirected to betting/crypto broker sites

Most of, if not every commit of claude code is now written by claude code itself without any human writing code, only promoting.

Windows is just a wonderful box of chocolate that keeps expanding. You never know what you get, all brilliant frontier tech innovations like Edge, Bing, the calculator, vertical taskbar, and now the highly intelligent Copilot, up there fighting with OpenCode, CC and others...!