rabf

That was the Nvidia 580 driver, its a known issue. 575 dirver is working fine.

The file chooser can be somewhat tamed in the settings editor. For example to get the buttons back to the bottom of the dialog where they belong: disable the "DialogsUseHeader" setting under "xsettings" in xfce4-settings-editor

Make sure you have a HiDPI theme selected and that you set a custom DPI that matches your screen in Settings->Appearance->Fonts.

When people ask what computer they should buy I always tell them to get any old office computer from ebay and use the rest of the money to buy a really nice monitor, and a really nice keyboard and mouse, as these are the bits you use! For most tasks that are undertaken on a computer any processor from the last 10 years coupled with 16GB of ram is more than sufficient.

`glow` is a pretty handy terminal mardown viewer.

Codex is included with the $20 a month chatgpt subsciption with very generous limits.

Positive reinforcement works better that negative reinforcement. If you the read prompt guidance from the companies themselves in their developer documentation it often makes this point. It is more effective to tell them what to do rather than what not to do.

His application `boomer` is the best desktop zoom app for X11! Bound to a keyboard shortcut its very useful for debugging graphics layout errors during development.

I've always walked to the shops by pulling the earth around beneath my feet!

There really isn't many concepts to get. `zpool` is like the device manager, use it define how your disks are grouped i.e. turn two disks into a mirror or striped array. `zfs` creates, sets properties on and manages the datasets on the zpool.

For Linux specifically I also reccomend https://docs.zfsbootmenu.org/en/v3.1.x/.

ZFSBootmenu is a bootloader that is fully able to take advantage of all the ZFS features and it also has great documentation with installation guides for a range of distros. https://docs.zfsbootmenu.org/en/v3.1.x/guides/fedora/uefi.ht...

I reccomend you just play around with it a bit first (you can just use some 1Gb test files instead of actual disks), its really just a lack of familiarity that scares people away.

AMD used to be terrible on Linux, perhaps before your time. Nvidia was always the choice if you needed functional hardware acceleration that worked on par with windows. The nvidia driver was/still is? the same driver accross platforms with a compatibility shim for each OS. This is how Nvidia managed to have best in class 3D acceleration accross Windows, FreeBSD, and Linux for decades now. OpenGL support historically on AMD was really bad, and AMD support was through a propriety driver back the day as well. Part of the reason the AMD/ATI opensource driver gained so much traction and support was that the propritery driver was so bad! Then you get onto other support for things like CUDA for professional work which Nvidia has always been light years ahead of any other card manufacturer.

Source: Was burned many times by ATI's promises to deliver functioning software over the years. Been using Nvidia on Linux and Freebsd for as long as can recall now.

Try just setting the correct dpi for your monitor and use a hi-dpi theme. No scaling required. Pixel perfect graphics.

Fractional scaling is a really bad solution. The correct way to fix this is to have the dpi aware applications and toolkits. This does in fact work and I have ran xfce under xorg for years now on hi-dpi screens just by setting a custom dpi and using a hi-dpi aware theme. When the goal is to have perfect output why do people suddenly want to jump to stretching images?

I found thst ZFS to be very simple to understand, everything is controlled by just two commands. Datasets are huge win over partitions which seem like such a weird relic of the past once you have tried datasets. Fairly confident you can grasp ZFS in a hour or 2, you can even make a zfs pool from files to mess around with.

Nice site, runs very smoothly on Firefox.

A lightweight GTK Linux chat client that is not based on any web tech and supports most of the features offered by the various API's out there such as audio and image gen.

https://github.com/rabfulton/ChatGTK

I'm sure the code can be critisized, but I'm happily using the application I wanted that did not exist having never programmed python in my life.

You do realise they can search the web? They can read documentation and api specs?

"the knowledge they use does need to exist somewhere in training data", I'm not to sure about that. The current coding enviroments for AI give the models a lot of reasoning power with tooling to test, iterate and web search. They frequently look at the results of their code runs now and try different approaches to get the desired result. Its common for them to write their own tests unprompted and re-evaluate accordingly.

That depends a lot on the system prompt and the tooling available to the model. Are you trying thin in Claude code or Factory.ai, or are you using a chat interface? The difference in the outcome can be large.

To add to this: the tooling or `harness` around the models has vastly improved as well. You can get far better results with older or smaller models today than you could 10 months ago.

I used to to compose midi on Cubase on my Atari st with 512kB of ram. Probably had far more features and ran snappier to boot!

It has also made it easier than ever to build native applications that use the os provided toolkits and avoid adding a complete web-tech stack to everything.

There is plenty of well optimised software out there already, hopefully a ram shortage can encourage people to seek it out. Would be nice if there were some well curated lists of apps. Sort of like suckless but perhaps a little less extreme. A long standing problem in the software industry is developers havein insanely overspecced machines and fat interne popes leading to performance issues going unnoticed by the people that should be fixing them. The claim that they the need that power to run their their code editor and compiler is really only a need for a code editors and compilers that suck less. I've always ran a 10 year old machine (I'm cheap) and had the expectation that my debug builds run acceptably fast!

Thats a problem with youtube not your gpu!

Completed in 2007.

https://www.x.org/wiki/ModularizationProposal/

If you have the paid subscription you can choose what model your question is routed to. Current options in the UI are GPT-5.1 Instant, GPT-5.1 Thinking, GPT-5 Instant, GPT-5 thinking mini, GPT-5 thinking, GPT-4o, GPT-4.1, o3 and o4-mini. Options like deep-research will affect the reasoning level used. There is a lot that goes on behind the scenes in the chatgpt app with things like tool use or function calling coming into play as well. Ultimately what OpenAI will be trying/hoping to do is give you a satifactory result using the least amount of compute possible - this is where the autorouter is very useful for them and obstensibly for the user who would not know which one to pick. I mostly just use the API's these days as I like to be the one who decides who/what I am talking to.

Working on a lightweight gtk3 AI byok client application for linux.

https://github.com/rabfulton/ChatGTK

Chatgpt is not one model! Unless you manually specify to use a particular model your question can be routed to different models depending on what it guesses would be most appropriate for your question.