If I’m not going far, not driving or not planning on spending much then yes, wallet stays at home.

Otherwise, if I’m driving then I’m taking my driving license with me (you never know), if I’m making a purchase over the contactless limit then I need to take my actual card with me anyway, or if I’m away for a longer period then I might need cards that I don’t have linked to my phone (like my corporate card - like fuck am I putting that in my phone).

And for all that, I’d rather have a wallet instead of just a loose amalgamation of plastic in my pockets.

Apart from the times that the US applied export controls to encryption software.

I like my geese free and thriving

There’s a lot to cover here but I’ll try to touch on each point:

The key requirement is fast memory that can be addressed by your GPU, and ideally a lot of it - hence the insane cost of this hardware right now.

Remember that you need space for the model’s weights (think of this as its ‘knowledge base’) and the context window, which is basically the data needed for the LLM to keep track of your current conversation with it (effectively its short term memory).

With smaller pools of VRAM (8-16gb) you will have to compromise and either have a more capable model that will lose context quickly and start hallucinating, or a less capable model that can maintain a session for a bit longer but overall less ‘smart’.

For software - there are a couple of options for running the LLM itself, Llama.cpp is one of the more popular tools and is the one that I use. It has a web UI with the usual chat interface, and also exposes an API that you can plug other tools (e.g. opencode) into, depending on your use case.

In terms of hardware recommendations, at 20GB+ of VRAM you do have a bit more headroom compared to more consumer grade GPUs, but to be honest the most cost effective way to get a shitload of VRAM is likely not with a dedicated GPU but actually using a system based around a recent APU.

I got a Minisforum MS-S1 last year for exactly this purpose. It is based on AMD’s Strix Halo platform which it has in common with the Framework Desktop and a couple of other similar devices.

It has 128gb of unified RAM which can be divided between the GPU and CPU however you like, so plenty of capacity for even fairly chunky models. It also uses a tiny amount of power compared to a more traditional system with a dedicated GPU, while also giving really reasonable performance for most AI workloads, more than enough for use in a homelab.

For cloud rental - doable, but pricing is a factor, and of course this will not actually be running locally.

Usability - manage your expectations, but overall for a lot of use cases and of course depending on the model that you are running and the resources you throw at it, it can be comparable with especially older iterations of ChatGPT, Gemini etc.

But remember, you are not a Google or an Anthropic and do not have an infinite pool of compute to throw at your model, nor do you have access to the specific models they are using.

He is the manifestation of the ‘I made this’ meme. Among other things.

Personally any game that requires a rootkit in order to play is not a game I’m interested in, from either a gameplay or a security point of view.

As others have said, 100% a leak.

I would advise to stand on a chair or stepladder underneath the ceiling and check to see if it is still level. If you see an obvious deformation around the stain, this will be being caused by water pooling on top of the ceiling plasterboard. In which case, once the leak is sorted, you will likely need to drain the pooled water, cut out the damaged section, replace it, then replaster and repaint.

We had exactly the same issue in our last house. It was in a difficult to see spot hidden behind our kitchen cabinets. We only realised the severity of the issue when the ceiling boards gave way and fell on my head.

There are only two industries that call their customers ‘users’…

I dunno, I reckon ‘DRAL YAES’ goes harder

Hot take: Nintendo peaked with the Wii.

No shit. Chess programs are specifically built and optimised to the nth degree for this specific use case and nothing else. They do not share the massive compute overhead and convoluted nondeterministic nature of an LLM.

This is like drag racing an F1 car and a Camry and being surprised at the result.

Because, unless you’re driving a forklift, the point of a vehicle’s rotation is in line with the rear wheels, meaning you can take turns at a much more acute angle when reversing than going forwards. Which makes backing into spaces much easier.

Notice that most of the half-assed parking jobs you see are generally people who have driven forward and left the car parked at a diagonal half out of the space, because getting the vehicle lined up in that situation is more difficult.

The main issue was a catastrophic failure of the VC_FRONT module which is one of the critical onboard computers that manages things like the 12v battery and low voltage power distribution (basically a “smart” fuse box). Without it the car is bricked and cannot be driven.

That took several weeks and some back and forth around the extended warranty to resolve, and then even after that module was replaced, on my first drive after the repair it went straight into limp mode and then spent another week at the service centre having that diagnosed.

During this time I decided it might be time to start looking for a new car, ended up selling it a few months later and took delivery of a new Polestar 2.

I’m not sure why anyone expected a new facelift would improve sales. It’s clear the overall decline is associated with Musk going full mask-off fascist, given this, driving around in a car that looks unlike any previous Model Y just makes it completely obvious that you knew this and decided to buy one anyway. If they want to bolster sales, maybe they should have kept producing the pre-facelifted versions for a while.

Full disclosure, I used to own a Model 3. I had it for 5 years and was generally very happy with it - it was a great daily driver, cost very little to run and maintain, and (aside from a few issues later in my ownership, which was one of the reasons I decided to sell it) in general it was very easy to live with.

There are clearly some very skilled engineers at Tesla who know how to build a great product. It is a shame their efforts are being undermined by a fascist lunatic with a narcissist complex.

Old? Check. Male? Check. Hung out on Epstein island? Check.

Seems like a perfect match to me.

Well, I’m currently writing a service and frontend, both in C# (Blazor for the UI), and using docker-compose to build and deploy them to a Raspberry Pi running Linux. So not only cross-platform, but cross-architecture as well.

This is not a new thing either. Since .NET Core was released almost 10 years ago, it has supported cross platform development.

Assuming your Fiesta produces < 100g/km CO2, looks like you’ll now be paying £20/year (as it was manufactured before 2017, different rules apply) - could be worse!

Not quite. Even existing EVs (with some exceptions for older vehicles) will be charged the new basic VED rate of £195 when they are next due to renew (which could be in up to a year’s time).

What EV purchasers were trying to avoid was the expensive vehicle supplementary tax of £425/year for cars with a list price of over £40k, which EVs purchased/registered since the start of April are no longer exempt from.

As the vast majority of new EVs on the market fall into that price bracket (including all Teslas except the base tier Model 3), suddenly the yearly tax for most new EV purchases jumps from £195 to £620/year.