Everybody forgets Jules.

That's definitely the right way to do it, I've had exactly the same experience.

Congratulations on launching the front-end, but I don't see how it can be made for developers and not have a Linux version.

I've never used a single linux GUI app in my 15 years of developing software. No company I've worked for even gives out linux laptops.

Its very strange, but they do have a Linux client that they refuse to mention in their blog post. I have no idea if this is a simple slip-up or if it was for some reason intentional.

https://ollama.com/download/linux

This link is for the existing cli version, not the new gui app.

FWIW, I have the book and I've found it a really good read so far.

Stylewise, It reminded me of reading the original PragProg Rails book back in the day.

It's mostly finished. I just saw it's 40% off this week with the code 2025PERSPECTIVES at https://pragprog.com/titles/ldash/ash-framework/

Always happy to hear about people liking the book!

Something I've noticed is that Gemini through gemini.google.com or through the mobile apps is vastly inferior to Gemini through aistudio.google.com. Much worse handling of long contexts amongst other things. Very odd that a product that is free (AI Studio use is free), is much worse than the product I am paying 20 quid a month for.

I find this to be especially true for the newer models like "gemini-2.5-pro-preview-03-25", so if you haven't tried AI Studio yet, I'd give that a go.

Why does Google even have these two different interfaces?

AI studio is not a consumer interface. It's targeted at people building products that integrate LLMs.

They also have Vertex AI for the same thing.

Google seems to do a lot of "shipping the org chart" externally.

Every time I think, maybe I'll get a subscription, I read something like this and ask why?

It's still there.

Where it says "Thought for 20 seconds" - you can click the Chevron to expand it and see what I guess is the entire chain of thought.

Per OpenAI, it's a summary of the chain of thought, not the actual chain of thought.

Just be aware you don't get to use all of it. I believe you only get access to ~20.8GB of GPU memory on a 32GB Apple Silicon Mac, and perhaps something like ~48GB on a 64GB Mac. I think there are some options to reconfigure the balance but they are technical and do not come without risk.

This is an important consideration. Thanks for mentioning it.

I would use this. Is there anywhere in Goa I can verify my passport? Or maybe in Mumbai / Dabolim airport?

We'll arrange for an agent in Mumbai/Goa.

Simply purchase the product, finish your setup and speak with your assigned account representative.

They'll get you activated

Great stuff - and training was so cheap too - it would have cost less than $200 on Runpod, and half that price on spot instances.

I guess it's time languages other than Python, especially niche ones, started collating their own language specific datasets.

Personally, I daydream about an Elixir specific LLM I could run locally, trained or fine tuned to respond in an idiomatic fashion, and plug into a tool like Cursor.so.

Are there any examples of the internal dataset used in the 80K instruction / answer pairs Phind used to tune this?

With the prevalence of Wayland, I don't think it's correct to say that most Linux users will never encounter problems with NVIDIA. Things have improved recently but Intel and AMD are still way ahead when it comes to that.

I have not seen any evidence yet that Wayland is an improvement over X Window System, while for NVIDIA there are a large number of available software packages that are known to provide useful functions.

Very slowly, the AMD GPUs become usable with important applications, like Blender, but the problems that can be encountered when trying to use such applications with AMD GPUs and trying to accomplish something concrete are far more annoying than the fact that Wayland may not work well, because one can always choose to avoid Wayland without losing anything.