I tried using ollama because I couldn't get ROCm working on my system with llama-cpp. Ollama bundles the ROCm libraries for you. I got around 50 tokens per second with that setup.

I tried llama-cpp with the Vulkan backend and doubled the amount of tokens per second. I was under the impression ROCm is superior to Vulkan, so I was confused about the result.

In any case, I've stuck with llama-cpp.

It depends on your GPU. Vulkan is well-supported by essentially all GPUs. AMD support ROCm well for their datacenter GPUs, but support for consumer hardware has not been as good.

There's emerging work on using the quantum analogue for trits (qutrits) in quantum computing.

They are more robust to certain errors.

I've definitely caught myself bullshitting in the past. It may be difficult at first, but saying "I don't know" is very important.

You can use a firefox extension to bypass that popup as well as other paywalls.

Real World OCaml (https://dev.realworldocaml.org/) is a great one.

From the FAQ: "Not yet. For now, we’re focused on delivering the best experience in Visual Studio Code only."

I do hope they feature others at a later date, especially since they are planning to develop a commercial version.