_1

he's a well known author on LLMs already.

There's more python and typescript in the training data than bytecode.

This MCP server for Safari is pretty neat. I think I'm going to start automatting some tasks for our corporate websites.

With my younger coworkers it's their defence when I push back on them.

Salary band?

source?

It's not like they aren't going to support any new purchases.

Taxes are not a punishment.

That's from the Far Side. My mom has had this on her fridge for at least 30 years.

Same. two drinks and I'm done

My experience with them is that the are taught to cover as much syntax and libraries as possible, without spending time learning how solve problems and develop their own algorithms. They (in general) expect to follow predefined recipes.

I take it they meant pre-recorded. It was definitely scripted and practiced.

You might need to play around with the default settings. One of the first models I tried running on my Mac was really slow.. Turns out it was preallocating a long context window that wouldn't fit in the GPU memory, so it ran on the CPU.

We had this at Clemson University about 10 years ago. I think the whole design came out of an MIT lab though. There's video of it still up here: https://www.clemsongis.org/clemson-sandbox

I've noticed an uptick on emails with random mid-sentence bolding and more bullet lists.

> and with the goal you'll all finetune it for your use case.

What use-cases are a good fit for finetuning this model? More specific instruction following, knowledge from proprietary data, response tone?

We do use WebLLM and a hosted Weaviate database, but there are complaints about speed (both retrieval and time to first token as the context will get big). The Gemma 3n "nesting doll" approach sounds like it could be useful .. but haven't found anyone specifically doing it to add domain specific knowledge.

Which small model is good for fine tuning to various enterprise data sets? Our business units are wanting to run small models in browser and on mobile devices, without dealing with RAG and cloud resources.

If you need to support several languages, you're going to have to have a zoo of models. Small ones just can't handle that many; and they especially aren't good enough for distribution, we only use them for understanding.

Same as this https://github.com/minio/minio ?

It's called the Coriolis effect.

Kinda of strange to pick an example that is just wrong. It's supposed to be written from 1840 and says Paris is the seat of Napoleon almost 20 years after he died.

Pretty basic stuff that you'd been in a blog post from 2022.