Well it came to me that I could write that as an extension with Claude Code. And it's showing good progress.
HN user
pantulis
A hacker from Madrid.
The "per container" number of features that come to mind is never ending. For example, I'd love to have something like Safari's "Profile bookmarks" that allow you to set a different subset of your global bookmarks as the root of your bookmark bar per profile. This is insanely useful.
The TE reference is strong!
"Where we're going, we don't need eyes to see".
Being a Mac switcher since 2003 I am as much of a fanboy as anybody else but this quote from the article caught my attention, and smells like PR.
Many AI tools are also Mac-first or Mac-only
I fail to recall AI tools Mac-only general purpose AI or agentic tools. Most of the claws, harnesses, studios and inference engines seem to be multiplatform. You can say you can run then in a Mac with a nicer UI wrapper or whatever, but "Mac-first" or "Mac-only"?
This. It's like you end up growing your own PAUSE button for the rest of your day and you can break your own fourth wall.
I am a huge fan of Copilot CLI. It just feels so logical and low-friction to use compared to Claude Code.
Honest question, can you ellaborate? If given the option, I use OpenCode but what do you find in Copilot CLI that makes you prefer it to Claude Code?
What, did Korg release an M1 Max? How did I miss it?
It’s providing the inference of Anthropic models
DwarfStar is the only thing I've run that doesn't try and make my Mac Studio 128GB take off. Yes, it gets hot while doing inference but quickly cools down when idling, something I haven't experienced with Ollama, LMStudio or OMLX.
I was just curious and checked The Old New Thing archive... yes I've been reading Raymond Chen's stories for as long as I remember but hey, it's been 23 years of delivering consistently solid stories about Windows.
He's a lifelong familiar name since the LZEXE days.
How are 3 developers going to sell that to any company? Procurement will have a field day.
Apple will solve the issue as soon as they decide to monetize Siri AI with additional paid services.
EU wants Apple to open 'Siri AI', with access to a personal context, open to other model/AI providers.
Not sure this is the case. My understanding is what the EU wants is that users can use Siri AI or a third party AI service from, say, Anthropic or OpenAI, at the same level of capabilities, just as you can switch default browsers. It's not about the underlying LLM (that would be the huge privacy concern), it's about the product built on top. Of course how a third party AI gets its data from the device would need to be approved by the user and that third party AI provider would have to justify what it's doing with that personal data to the EU watchdogs, just as Apple would need to do.
The worst managerial practice is to use OneDrive for company work purposes. For anybody else than the original creator these docs are nowhere to be found unless you know the shared URL.
Exactly this!
AFAIK Sharepoint doesn't have these limitations. The idea is that in companies OneDrive should not be used for permanent stuff. Which is strange, to be granted, but after all using OneDrive for company documents basically means they are being shared out of some personal space that doesn't belong anywhere.
I'm personally waiting for the OpenSpark.
As are all consulting firms, to ve fair
The post goes to the point. Somehow this must be buried in Anthropic's documentation but I miss this kind of back-to-basic posts. Even if they are LLM-penned.
Even if it was the same --I think it's not-- you'll need a "SIBE operator license", and cannot do it solo, you have to be an employee of an authorized firm (bank, broker or dealer).
Nobody gets fired from hiring Kyndryl.
Agreed, and disappointed not to see the black bar. Moler was one of the greats.
I am under the impression that the end game will look a lot like Apple's closed ecosystem. They are reinventing filesystem permissions, networking security, but most importantly trust on extensions provenance.
Probably a good thing but it will remove a lot of the fun.
Love how the post begins praising Anandtech, then proceeds to write the rest of the content as if it was written by Anand himself. Great nod!
Even so, it is incredibly hard to prove workers 40 and older were laid off as a result of age discrimination.
The only way for this to happen is by leaked private conversations, I think.
eval, send, method_missing, define_method , as a non-rubyist how common are these in real-world code?
Quite a lot, that's what allows you to build something like Rails with magic sprinkled all around. I'm not 100% sure, but probably the untyped JSON ingestion example uses those.
Remove that, and you have a very compact and readable language that is less strongly typed than Crystal but less metaprogrammable than official Ruby. So I think it has quite a lot of potential but time will tell.
IMHO you should just write your own harness
Can you point to some online resources to achieve this? I'm not very sure where I'd begin with.
This weekend I installed Hermes on my computer. My M4 Max Studio started spinning its fans as if it wanted to fly, so I went for some cloud hosted models. The thing works as advertised, but token consumption is through the roof. of course ymmv depending on the LLM you choose.
But my main takeaway is that from the security standpoint this is a ticking bomb. Even under Docker, for these things to be useful there is no going around giving it credentials and permissions that are stored in your computer where they can be accessed by the agent. So, for the time being, I see Telegram, my computer, the LLM router (OpenRouter) and the LLM server as potential attack/exfiltration surfaces. Add to that uncontrolled skills/agents from unknown origins. And to top it off, don't forget that the agent itself can malfunction and, say, remove all your email inboxes by mistake.
Fascinating technology but lacking maturity. One can clearly see why OpenAI hired Clawdbot's creator. The company that manages to build an enterprise-ready platform around this wins the game.