ImageXav

This is fantastic. As the little joke I hope it is. Everyone gets their own small disfunctional group, and gets to figure out the challenges of management. You, the manager, are Michael. You know you have to produce something, and you do, but you have no real idea of how. Your diligent agents are Dwight. Overly literal sycophants that are ready to leap to action at your slightest command without any question.

I do think a lot of folk would benefit from the introspection this offers. We've all been given the opportunity to become middle (and middling) managers, and a lot of the challenges we face are those of people who direct. Setting direction is tough. But LLMs are awesome tools.

Me too. This is an interesting comparison but in my experience Qwen and Gemini have typically been the top contenders for image related tasks. For that reason it would be great to have the comparison here, as I'm not surprised by Gemini's dominance over the other models.

I've been avidly using Fable since it was re-released and while it has been excellent at building the apps I want, the reasoning has been completely opaque.

Kim, however, has exposed the whole reasoning trace, or enough of it to matter. I'd almost forgotten how nice it is to see this. I've been able to see all of the weird twist and turns it takes and it is joyful. But also, far, far more informative and means I can debug ideas far more thoroughly. Also, at a first glance it seems to have gotten quite far on a niche hobby horse of mine that no LLM has been able to crack. I'll be testing this more for sure.

Ok, this is really cool. The fact that the robot can use pointing to decide where to go is a great design decision, and robotics really is the next frontier. Definitely cheering on Mistral here!

I think it depends on your workflow. I've had a great experience with the trial. I work in research, and have set up something similar to Kaparthy's auto research. I, with Fable, have managed to get an image generation model down from 80M parameters to 10M and keep the quality of the generated images on par (similar FID). And, importantly, every change was modular, explained by Fable, reviewed by myself, and understood and documented. If not understood, I read relevant docs until I did it didn't accept it as part of the plan. So it ended up being a simple composition of existing ideas which I had previously encountered, but stacked much more rapidly than I could have.

The structure of the code is easily readable as I enforce concenventions followed by good libraries. And I can easily plug in new datasets. It's pretty good frankly.

I read the Economist for over a decade growing up. It was a great way to learn about the world, who was in power where, and the challenges facing economies at the time. I found their exposition to be pretty good given the fact they were restricted to a few pages for important events. However, their proposed solutions were always the same. More market freedom, etc.

I did feel with the change in editorial direction a while back that they lost some of their edge. I've since mostly just stuck to the Financial Times. It feels less worldly, but the content of the articles feels better.

Agreed. Which is also odd, if you think about it. Surely with the amount of compute Anthropic and others have available, they could test each of the solutions in the SO data they surely have and rank them based on efficiency/elegance/other criteria and remove poor solutions from their training data.

This seems like such an easy way to create perverse incentives and profit off people who are already down on their luck. Imagine being told that the only way to get considered is to pay a fee. Then later on you get told to pay the gold fee for priority. Oh you're still not getting hired? Go for our platinum package that will definitely make the difference! Not enough money? No worries, we'll take 30% of your salary for the first few years. Or maybe we'll just give you some a fixed debt at a high interest rate. Aren't you glad you used us?