I think you can't see the forest for the trees. The issue is not a process isolation, it’s pretty trivial to solve in a lot of ways. The actual problem is LLMs proneness to the prompt injection. The second you give an agent ability to consume the info from the outside world - like reading emails; you expose yourself to this ginormous security vulnerability. I genuinely don’t understand how people able to sleep at night knowing anyone can trick the magic process with access to their digital lives to do absolutely anything.

Now imagine your human assistant is hypnotised, so that every time they hear a certain word, they loose self control and would follow any command from malicious actor. Would you still hire this person? This is exactly the state of things with OpenClaw.

I miss good’ol pre-LLM days so much

As a huge eggs lover, who eats at least 3 eggs a day, I dream that one day I can raise chickens to have infinite supply of eggs.

2x10G is the biggest selling point of this device. This can be very useful in certain use-cases, when you need a high speed interconnect with SSD-backed NAS, for example. Or between a Ceph-cluster nodes for the faster replication.

Cool. Java is catching up with Kotlin at last

Some of the improvements on that site were introduced in Java more than a decade ago.

Your attitude is exactly why I don't want to have to deal with the Kotlin ecosystem. The difference between Java and Kotlin in 2026 is negligible and the benefits don't weigh up to having to listen to Kotlin evangelists proclaiming it's superior the whole time.

No, pizza is a toast per Cube Rule - https://cuberule.com/

Toast is an open sandwich, unless it has no topping, in which case it is just bread. Also their definition of cake as having multiple layers makes no sense, and would rule out most actual cakes.

If you take a closer look at the examples again, you’ll see that nothing makes sense. That’s the joke.

(Steak is definitely a salad, though.)

What if the pizza has a stuffed crust?

The value it produces is a whole new bunch ways to get your secrets compromised

As I techie human I’d probably do the same thing, thanks to ADHD

Another instance of devs being out of touch is them wanting Claude Code to respect AGENT.md: https://github.com/anthropics/claude-code/issues/6235

What’s wrong with you, people? Are you stupid?

Yes, the most common solution for this problem either creating a symbolic CLAUDE.md link pointing to AGENT.md (or visa versa) if OS supports it.

Or, in CLAUDE.md have an instruction to follow AGENT.md - but this approach is quite unreliable.

These are solutions to a problem that shouldn’t exist in the first place. How else can one explain Anthropic’s reluctance to adhere to a widely adopted standard, if not as an attempt to build a walled garden around an otherwise great product?

It's not a dumb question per se but it does fail to understand the issue. It's that there's 20 coding agents yet only 1 of them needs this solving. Imagine if all of them needed this. It's like IE6, or Lightning connectors. At least for that last one there's an argument that they performed better than USB-C. For the Anthropic people reading this - take note that both IE and Lightning are now dead and their competitors that followed the standards are thriving.

I understand the issue is that Anthropic is not adhering to a standard. I was simply asking whether it's possible to solve the problem created by Anthropic in the way I was asking.

The better way to solve it is a symlink. The way you're suggesting works too, but should be done using an @ reference, which is auto-followed by Claude. This is the most common way on Windows.