I know. I have NodeBB as a backup.

I imagine that was part of it, but I doubt it’s the actual main reason. More of a post justification.

Or if you just ignore federal courts, which seems to be the current fashion.

This is why some cities have banned the rental services. Paris has plenty of electric scooters, but they banned the rental services. Keeps the benefits of the scooters for micro mobility, but no scooters lying everywhere.

Rclone can do file mounts as well as sync.

A lot of the answers here are short or quippy. So, here’s a more detailed take. LLMs don’t “know” how good a source is. They are word association machines. They are very good at that. When you use something like Perplexity, an external API feeds information from the search queries into the LLM, and then it summarizes that text in (hopefully) a coherent way. There are ways to reduce hallucination rate and check factualness of sources, e.g. by comparing the generated text against authoritative information. But how much of that is employed by Perplexity et al I have no idea.

I feel like this article is exactly the type of thing it’s criticizing.

I think you have the wrong full generation parameters here.

Can you link the feeds?

The problem is that while LLMs can translate, it’s still machine translation and isn’t always accurate. It’s also not going to just be for that. It’ll be applying “AI” to everything that looks like it might vaguely fit, and it’ll stifle productivity.

Is the code available somewhere?

Well when Roosevelt was elected 4 times, it was actually legal back then. And he’s the reason why the 2 term limit amendment exists. But of course, that requires actually following the law, so…

Because of the porn or AI? 🙃

This is probably one of the best actual uses for something like generative AI. With enough data, they should be able to vectorize and translate dolphin language, assuming there is one.

1 scenario tested is better than 0 tested.

This guy would fit in well at my previous job where the founder discouraged writing unit tests because “there are too many scenarios to test.”

Like, wtf…

That was entirely the point unfortunately.

It’s enough to run quantized versions of the distilled r1 model based on Qwen and Llama 3. Don’t know how fast it’ll run though.

Don’t know about “always.” In recent years, like the past 10 years, definitely. But I remember a time when Nvidia was the only reasonable recommendation for a graphics card on Linux, because Radeon was so bad. This was before Wayland, and probably even before AMD bought ATI. And it was certainly long before the amdgpu drivers existed.

Please bring back the overflow menu!