coderbants

Interested to know throughput on 7900 XTX and what setup you're using?

Terminal is a significant risk though and I’d still really like to see macOS improve the APIs around filesystem access.

Granting terminal full disk access grants arbitrary scripts full disk access. There’s a lot you can do with ACLs and the permissions system, but it’s not reflected in the UI for settings.

Then there’s allowing access to documents, downloads, desktop, external disks. This should really allow the user to select a path or paths for applications, because these options are way too broad (especially external disks).

I think the lifecycle for these chips could stretch far longer. If you're offering these models on a two year lifecycle, then you'd be able to stand up your top tier (wouldn't need to be frontier) at high speed. Run (for example) Kimi K3 on it and give it a brand name:

AcmeAI Carbon

Market it as your premier (only) model at high throughput. Two years later you stand up MSICs for the new state of the art with entirely new hardware, your lineup becomes:

AcmeAI Nitrogen (top tier) AcmeAI Carbon (mid tier)

If you just kept pushing the same model down your pricing tier over time you could still extract a lot of value from an old model, even years after it's been set in stone. Working on brand new code/frameworks? Pay to use the newest model. Working on legacy code? Use the lower tier models that will already know your legacy frameworks, pay far less and still get massive throughput. I've worked on a lot of government projects that this would be absolutely brilliant for.

The other side of this is that agent harnesses are NOT set in stone, so even a legacy model with a knowledge cut-off that's years out of date can likely still be helped quite a bit by harness and fetch behaviours that are still developing rapidly. Especially at this kind of throughput.

This is a net good for Linux.

Most of the PC gaming audience is on Windows, so Windows is still the primary target being developed against. Having better Vulkan on Windows means more support for Vulkan in games in the pipeline, which means better Linux support in those games over time, which ultimately benefits Steam and their hardware.

I just use hyphens all the time and always have. I don’t like that AI loves em dashes so much that it looks like everything I write now is AI generated, but if you were to deep dive you’d notice I’m using hyphens - never em dashes - so my writing can’t be AI. Granted you’d have to be pretty pedantic to care in the first place but it’s 2026 and here we are.

A friend of mine in college had the same CRX as the author and I’d get rides to campus with him. He passed away in an accident not long after the first Fast movie came out. I totally get what the author is saying about some cars being time machines/memory capsules.

Name checks out.

It cuts both ways. Sometimes I ask Gemini 3.5 Flash to do something for me and it kicks it out almost instantly and it works great, and it's a bit scary how quickly it can do that.

Then I ask it to do something else and it goes off-road and where I used to be able to interject with a "wow wow wow, that's not right", by the time I see the text on screen and react it's already made massive changes. Short of making it commit between every edit it's hard to prevent it from going wrong as quickly as it goes right (and even then, it can make a boo-boo on a remote API too depending on how much privilege it has).

I get the debate in this thread but this is IMHO the detail that matters:

"Many of these companies don't even have an external API! And yet, they're all building MCP servers."

Whether or not MCP is a temporary means to an end or a more permanent standard is kind of missing the point that the overall callable API surface is expanding rapidly. How it's called by the agent is an implementation detail.

Can’t you turn the 1M off with a /model opus (or /model sonnet)?

At least up until recently the 1M model was separated into /model opus[1M]

The idea is that the immutability of the operating system leads to greater stability. The partition should (in theory) be exactly as the distribution expects on every computer it’s installed to, which limits the potential for user changes breaking anything. The benefit to the user is that it’s a lot harder to shoot yourself in the foot by running the wrong script.

The issues have been described as login/logout, but I'm not sure that's all that's happening. In today's outage and the last the API stopped and kicked the session out.

I only mention this in case someone from Anthropic perhaps isn't aware that it seems to be a wider issue than login/logout (although I'm sure they are!)

If only my handwriting weren't utter chicken scratch I'd use this, but in my case - nobody needs to see that. :-/