I use Gemma27b currently with a custom agent wrapper and its working pretty well.

I run a game when players can post messages, it's a game where players can kill each other, and people often send threats along the lines of "I will kill you". Telling Gemma that it should classify a message as game related or a real life threat, and that it is for a message in a game where players can kill each other and threats are a part of the game, and that it should mark it as game related if it is unclear if the message is a game related threat or a real life threat does not work well. For other similar tasks it seems to follow instructions well, but for serious topics it seems to be very biased, and often err on the side of caution, despite being told not to. Sometimes it even spits out some help lines to contact.

I guess this is because it was trained to be safe, and that affects it's ability to follow instructions for this? Or am I completely off here?

I get the sense that AI is at the “hobby kit computing” stage where they used to dump all the components in a box and give you a schematic and a soldering iron and happily say “you make it work!”

And that worked in the early days of computing because there was a small number of people really motivated for the outcome.

But fully assembled and packaged and tested in a nice looking box is where the real demand turned out to be.

I’m looking forward to the day Google doesn’t just dump a model and say “you do the rest”.

I want to fire up Ubuntu on a Strix Halo and say apt install then load the browser interface. Or just download and run a Mac installer and have it just work.

Arcane complex multi step build install configure processes for AI need to end in favor of one click install. I’m not interested in the process of making it run.

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

If Gemini is going to repeat something at least its that the team is great, and not a disgrace!

Could it be tamed with good role-system prompt crafting? (Besides fine-tuning.)

That still requires more than 170 floppy disks for installation.

For sure it won’t generate great svgs, but it might be a really good conversational model

You'll get better results.

> This SVG code provides a clear and visually appealing representation of a pelican riding a bicycle in a scenic landscape.

My first try:

user: "When was Julius Caesar born"

response: "Julius Caesar was born in **Rome**"

Beautiful :D

(I do not mean to detract from it - but it's just beautiful. It will require more effort to tame it.)

Not sure how much data is needed to realistically fine-tune something like this and get useful output.

Then Siri just kinda languishes for forever, and LLM's pass the torch of "Cool Tech", so they try and "Reinvigurate" the team, but with no clear direction. Are they going to be a cloud provider? Are they going to contract out the training? Are they gunna spin up a compute facility even after neglecting to do so since 2012?

Apple needs to just stop trying shit, and just get that app store money. That's why jobs appointed cook. Jobs new cook was no innovator, but he could make apple a money printing machine. Thats what they should stick with.

If you have the latest betas installed you can call those APIs right now.

They also support fine-tuning on the model that ships with ~every device:

https://developer.apple.com/apple-intelligence/foundation-mo...

as mentioned in the blog post: > "it can execute tasks like text classification and data extraction with remarkable accuracy, speed, and cost-effectiveness."

input: ``` Customer Review says: ai bought your prod-duct and I wanna return becaus it no good.

Prompt: Create a JSON object that extracts information about this customer review based on the schema given. ```

output: ``` { "type": "review", "class": "complaint", "sentiment": -0.853, "request": "return" } ```

So essentially just "making sense of" natural language such that it can be used in programmatic context. (among other applications of course)

To get good results, you probably need to fine tune this model to expected data very aggressively.

The idea is, if a 270MB model can do with fine tuning, why ship a 32GB generalist model?

Are they?

My suggestions here are to hook this model up to a RAG system, then you can rely on an external knowledge store. Or you can try finetuning this model with the facts that are important to you, if you do that it should pick up that new knowledge quite quickly.

https://ai.google.dev/gemma/docs/core/huggingface_text_full_...