For the best experience on desktop, install the Chrome extension to track your reading on news.ycombinator.com
Hacker Newsnew | past | comments | ask | show | jobs | submit | history | manmal's commentsregister

Maybe I’m lacking imagination. But how will a GPU with small-ish but fast VRAM and great compute, augment a Mac with large but slow VRAM and weak compute? The interconnect isn’t powerful enough to change layers on the GPU rapidly, I guess?

> But how will a GPU with small-ish but fast VRAM and great compute, augment a Mac with large but slow VRAM and weak compute?

It would work just like a discrete GPU when doing CPU+GPU inference: you'd run a few shared layers on the discrete GPU and place the rest in unified memory. You'd want to minimize CPU/GPU transfers even more than usual, since a Thunderbolt connection only gives you equivalent throughput to PCIe 4.0 x4.


But isn’t the Mac Mini the weak link in that scenario?

It has way more unified memory than your typical dGPU.

Yes obviously. That VRAM is also slower and has weak compute attached. Loading to the external GPU will slow things down too much.

My Mini is actually the smallest model so it actually has "small but slow VRAM" (haha!) so the reason I want the GPU for are the smaller Gemmas or Qwens. Realistically, I'll probably run on an RTX 6000 Pro but this might be fun for home.

We've seen many recent projects to stream models direct from SSD to a discrete GPU's limited VRAM on PCs.

How big a bottleneck is Thunderbolt 5 compared to an SSD? Is the 120 Gbps mode only available when linked to a monitor?


That’s what, 14GB/s? The GPU‘s VRAM can do 100x that.

A discrete consumer GPU card doesn't have enough fast RAM to run a very large model that hasn't been quanitized to hell.

That's why all the projects streaming models into the GPU from an SSD popped up recently.


Yes. There’s just no way to get above 1t/s that way with a large model.

Graphics was not what came to mind when I saw the headline.

Graphics is typically what comes to my mind when people talk about graphics processing units

The latest MacBook Pros don’t even need external GPUs to run AAA games.

What do you mean when you say "run"? Low graphics 45 FPS at 720p? Or ultra graphics 120 FPS at 4k? My assumption is that a fairly large part of that space is inaccessible with the integrated GPU.

The term eGPU gives it away, but is inaccurate.

Something like eNPU or eTPU seems more appropriate here.


> not allow something like OpenClaw on our network

And where’s the difference between the Claude Desktop app and OpenClaw at this point? Anthropic have been hard at work porting the most important features. You can easily shoot yourself in the foot with both now.


We have a legal contract with Anthropic

OpenClaw and OpenCode are open source projects with zero warranty and nobody to sue if they have a npm Trojan in them


> OpenClaw and OpenCode are open source projects with zero warranty and nobody to sue if they have a npm Trojan in them

When has any technology company been sued for pushing accidental malware in their updates?

The reality is that you have never had anyone to sue.


Sure you did. But 99% of the time, you get the benefit of things that come with ability to sue - such as the vendor having a support team that's actually incentivized to respond to reports and deal with them quickly.

I agree with parent, "having a contract" gives you nothing tangible. Big tech providers get hacked quite commonly nowadays, some with glaringly embarrassing vulnerabilities like "the admin password was admin". All your data leaks, and the most you get from them going "sorry".

Having the ability to sue, and having the resources to sue is also not the same.

The amount of times I had to deal with support cases (as the reporter, not the handler) where I felt like the support person was actually incentivized to solve my problem vs just following the script is astonishingly low. Even with paid support. Paid support just means you get to follow their script faster.


So you don’t use any other open source software at all then?

The risk with OpenClaw et al isn't that the software itself is compromised. The risk is that what it does is fundamentally insecure and Claude Code isn't any better


That’s not the issue, the issue is that people are using their subscriptions (intended only for use with Anthropic products) with non-Anthropic products and this is simply Anthropic enforcing their ToS.

Good point. When it comes to npm Trojans you’re probably more likely to find them in dumb and boring deps like Lpad.

That's table stakes. LLMs are not like traditional software for fundamental reasons, and cannot be fully secured without destroying all value they provide.

Once again, despite everyone's protestations about not anthropomorphising things, LLMs are, to first approximation, best seen as little people on a chip. So with that in mind, it should be obvious why enterprise would prefer dealing with Anthropic's official products than OpenClaw - it's similar to contracting a team of software engineers from another well-known corporation and giving them keys to the castle, vs. inviting in any randos that show up at the door on any given day and can pass FizzBuzz test. Even if, in both cases, these turned out to be the same people, having an organizational/legal-level relationship changes the expectations and trust levels involved.


Claude Desktop is an Anthropic product, Openclaw is not (their founder works for OpenAI even).

Anthropic wants you to use their subscription only for Anthropic products.

I don’t think the difference is that difficult to see.


Both teams ship at breakneck speed and both randomly regress. I don't see such a big difference. Claude now uses Claude by default to judge whether a tool call is sane or not. At least OC is transparent about the insanity of running bash commands unchecked.

I guess parents point how dangerous OpenClaw is and that Claude Code is now similarly dangerous

They want you to do your shit through their own desktop apps.

Tell me you are not using Anthropic without telling me. Bursts of unlimited usage was never the case. And I bet their infrastructure doesn’t like bursts as much as more spread out activity.

Come on, someone on a Max account has a reason why they are paying $200. I bet many are at least often near the weekly limit, or they‘ll downgrade. If anything, OpenClaw usage is more spread out instead of ingesting whole codebases during office hours.

The Anthropic subs are likely priced at marginal cost (Amp‘s CEO recently said that in a podcast). It just doesn’t serve Anthropic to be operating as the service layer for OpenClaw.


The upcoming MacBook Pro (late this year) is rumored to have a hole-punch camera: https://www.macrumors.com/2026/02/24/touchscreen-macbook-pro...

It‘s reasonable to assume that menu bar items will be rendered differently as well, to accommodate for Dynamic Island (which changes its width as needed).


Compared to flaky bartender, I‘d prefer even that tbh.

There is no Max sub for enterprise AFAIK, are you using a private plan for work?

Yes. This seemed to be more cost effective.

It is. Those plans are probably priced at marginal cost. Enterprise is 4x the cost or more.

For some reason, MS is still doing well. I’m not sure what conclusions I should draw from that, other than big businesses are hard to kill?

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search:

HN For You