Viewing profile — ImageXav

This feels extremely close in nature to being a generalisation of discrete distribution networks. Paper: https://arxiv.org/abs/2401.00036 Project page: https://discrete-distributio…

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 expos…

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…

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, h…

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 the…

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 s…

Title. I finally got annoyed enough at work with a colleague who posted an 11 point list they clearly hadn't read or reviewed as a comment on my PR that my reply started with 'Than…

It may feel that way due to the iterative nature of medical improvements, but over the past few decades there has been a consistent reduction in cancer mortality rates across most …

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 t…

Agreed. One at a time testing (OAT) has been outdated for almost a century at this point. Factorial and fractional factorial experiments have been around for that long and give det…

I guess that's the crux of it. From an individual perspective it makes sense to stay in a stable environment, especially if a family is involved. However, I think from a societal p…

I would add an aspect that is not covered here but is often ignored: the strong labour protection laws result in a mentality where if you get a good job you are much less likely to…

This is an interesting point. I've been trying to think about something similar recently but don't have much of an idea how to proceed. I'm gathering periodic time series data and …

As per the title. I tend to travel a lot and don't often have comfortable access to my laptop. I would like to run quick, small research ideas quickly. My workflow would be: - Ask …

I've had the complete opposite experience, and feel the complete opposite way. What is there to learn from failing a leetcode? It feels like luck of the draw - I didn't study that …

Yes, especially as models are known to have a preference towards outputs of models in the same family. I suspect this leaderboard would change dramatically with different models as…

Thanks for sharing that. Interesting that the leaderboard is dominated by Anthropic, Google and DeepSeek. Openai doesn't even register.

How did you achieve that? I was looking into it and $0.006/min is quoted everywhere.

I feel as though it also represents the fact that contributors are less invested in the project. There was a small study done a few years back hypothesizing that the number of swea…

Even better, python has named tuples [0]. So if you have a tuple that you are sure will always have the same inputs you can declare it: ``` Point = namedtuple('Point', 'x y') pt1 =…

Not necessarily. Interpretability of a system used to make decisions is more important in some contexts than others. For example, a black box AI used to make judiciary decisions wo…

Something that stuck out to me in the updated blog [0] is that Demon Adam performed much better than even AdamW, with very interesting learning curves. I'm wondering now why it did…

I've found that YOLOv7 [0] tends to perform better across the board than anything ultralytics has produced, without the horrendous licensing. [0] https://github.com/WongKinYiu/yolo…