#local-llms

#local-llms

Asif on the other hand, is doing something else: He's doing things the Pybites way! He's building with a focus on providing value. We spent a lot of time discussing a problem I'm seeing quite often now: developers who limit themselves with AI. That is, they learn how to make an API call to OpenAI and call it a day. But as Asif pointed out during the show, that's not engineering. That's just wrapping a product.

Reviewing a Linux-powered laptop or PC is always a breath of fresh air to me, because I know the OS very well (so I know exactly what to expect) and it's almost always a positive experience from start to finish. The NX Gen3 was no exception. The model I received housed an Intel Ultra 7 255H, Arc T140 8 Xe CPU/GPU, with 32 GB of RAM and Mesa Intel graphics, which runs around $1,230.

As AI takes off, the whole cycle promises to repeat itself again, and while AI might seem relatively cheap now, it might not always be so. Foundational AI model-as-a-service companies charge for insights by the token, and they're doing it at a loss. The profits will have to come eventually, whether that's direct from your pocket, or from your data, you might be interested in other ways to get the benefits of AI without being beholden to a corporation.

ZIO uses a lightweight concurrency model based on fibers, enabling efficient execution of thousands of tasks concurrently on few actual JVM threads.