A Mac allows it to send iMessage and access the Apple ecosystem.

Can a Raspberry Pi run several browser tabs?

Really? That's it?

I think the mini is just a better value, all things considered:

First, a 16GB RPi that is in stock and you can actually buy seems to run about $220. Then you need a case, a power supply (they're sensitive, not any USB brick will do), an NVMe. By the time it's all said and done, you're looking at close to $400.

I know HN likes to quote the starting price for the 1GB model and assume that everyone has spare NVMe sticks and RPi cases lying around, but $400 is the realistic price for most users who want to run LLMs.

Second, most of the time you can find Minis on sale for $500 or less. So the price difference is less than $100 for something that comes working out of the box and you don't have to fuss with.

Then you have to consider the ecosystem:

* Accelerated PyTorch works out of the box by simply changing the device from 'cuda' to 'mps'. In the real world, an M5 mini will give you a decent fraction of V100 performance (For reference, M2 Max is about 1/3 the speed of a V100, real-world).

* For less technical users, Ollama just works. It has OpenAI and Anthropic APIs out of the box, so you can point ClaudeCode or OpenCode at it. All of this can be set up from the GUI.

* Apple does a shockingly good job of reducing power consumption, especially idle power consumption. It wouldn't surprise me if a Pi5 has 2x the idle draw of a Mini M5. That matters for a computer running 24/7.

> In the real world, an M5 mini will give you a decent fraction of V100 performance

In the real world, the M5 Mini is not yet on the market. Check your LLM/LLM facts ;)

An LLM would have got the Markdown list formatting correct.

HN doesn't actually follow Markdown. There's no list syntax here, you need to start paragraphs to imitate it.

Ehh, not “it” but it’s important if you want an agent to have access to all your “stuff”.

macOS is the only game in town if you want easy access to iMessage, Photos, Reminders, Notes, etc and while Macs are not cheap, the baseline Mac Mini is a great deal. A raspberry Pi is going to run you $100+ when all is said and done and a Mac Mini is $600. So let’s call it. $500 difference. A Mac Mini is infinitely more powerful than a Pi, can run more software, is more useful if you decide to repurpose it, has a higher resale value and is easier to resell, is just more familiar to more people, and it just looks way nicer.

So while iMessage access is very important, I don’t think it comes close to being the only reason, or “it”.

I’d also imagine that it might be easier to have an agent fake being a real person controlling a browser on a Mac verses any Linux-based platform.

Note: I don’t own a Mac Mini nor do I run any Claw-type software currently.

From x post:

“I made a tool that turns PCB designs into 3D-printable molds. you sandwich copper tape between the parts, sand the ridges, and you have a real working PCB. no etching, no chemicals”

I’m fascinated by the confidence in the cyborg theory that there will always be value in having a human in the loop. Especially for domains like code where the inputs and outputs are bits not atoms.

This is exactly what chess experts like Kasparov thought in the late 90s: “a grandmaster plus a computer will always beat just a computer”. This became false in less than a decade.

There are lots of things people want explicitly because a human is part of the loop. AI generated art will never attract the same premium as something created by (or at least claimed to be by) a human. People seek status, and that can only be conferred by other people. The problem is that, unlike other products of human labor, status is a zero sum game.

Chess is a "kind" learning environment. The world tends to have more "wicked" environments.

> I don't think this is something that LLMs can ever replicate. They don't have the egos and they certainly don't have the experience

Interesting question - the result is just words so surely a LLM can simulate an ego. Feed it the Linux kernel mailing list?

Isn’t back and forth exactly what the new MoE thinking models attempt to simulate?

And if they don’t have the experience that is just a question of tokens?

SO was somewhere people put their hard won experience into words, that an LLM could train on.

That won't be happening anymore, neither on SO or elsewhere. So all this hard won experience, from actually doing real work, will be inaccessible to the LLMs. For modern technologies and problems I suspect it will be a notably worse experience when using an LLM than working with older technologies.

It's already true for example, when using the Godot game engine instead of Unity. LLMs constantly confuse what you're trying to do with Unity problems, offer Unity based code solutions etc.

> Isn’t back and forth exactly what the new MoE thinking models attempt to simulate?

I think the name "Mixture of Experts" might be one of the most misleading labels in our industry. No, that is not at all what MoE models do.

Think of it rather like, instead of having one giant black box, we now have multiple smaller opaque boxes of various colors, and somehow (we don't really know how) we're able to tell if your question is "yellow" or "purple" and send that to the purple opaque box to get an answer.

The result is that we're able to use less resources to solve any given question (by activating smaller boxes instead of the original huge one). The problem is we don't know in advance which questions are of which color: it's not like one "expert" knows CSS and the other knows car engines.

It's just more floating point black magic, so "How do I center a div" and "what's the difference between a V6 and V12" are both "yellow" questions sent to the same box/expert, while "How do I vertically center a div" is a red question, and "what's the most powerful between a V6 and V12" is a green question which activates a completely different set of weights.

For younger kids I can heartily recommend the Hobbit illustrated by Jemima Catlin- has plenty of pictures to them engaged. Read it to my 6 year old and we’re now excited for LotR.

Oh, this looks excellent, thanks :-)

Anna’s Archive has largely flown under the radar by focusing on books.

Even perceived involvement in music piracy puts a much bigger target on their back from far more aggressive actors (RIAA, major labels)

The bulk of today's customers has no idea how to pirate music, so they're not really a threat anymore. Music streaming has been rather convenient, you pretty much get the same content across all services. Video streaming platforms have, unfortunately become fragmented and, as of late, ad-ridden.

“Good luck, we don’t care.” is their stance, as far as I can tell.

I'm curious what percentage of claude/codex users this is true for - I assumed their business models rely on this not being true for the majority.

Both Claude Code and Codex steer you towards the monthly subscription. Last time I tried Codex, I remember several aspects of it being straight up broken if used with an API key instead of a subscription account.

The business model is likely built upon the assumption that most people aren't going to max out their limits every day, because if they were, it likely wouldn't be profitable.

I got $250 free Claude Code credit and I was surprised by how hard it was to actually use it all before it expired.

It's a 1.7 trillion token free model. Why wouldn't you try it?

I've been testing free models for coding hobby projects after I burnt through way too many expensive tokens on Replit and Claude. Grok wasn't great, kept getting into loops for me. I had better results using KAT coder on opencode (also free).

> Why wouldn't you try it?

Because the people behind it and myself having at least some standards