HN user

pantulis

2,270 karma

A hacker from Madrid.

Posts0
Comments1,131
View on HN
No posts found.

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.

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"?

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?

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.

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.

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 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.

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.

GPT-5.5 3 months ago

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.