The powers of kerning are great indeed

You meant *keming [1], of course. :)

[1]: https://en.wiktionary.org/wiki/keming

It has nothing to do with this but ok ...

Nice idea!

I think it would be better if it was just context and not connected to any model. Think of one place where you can hook in your drive folder, GitHub, etc. and have it produce the best context for the task you want to achieve. Then users can copy that to their model or workflow of choice

Thank you, this could be a cool feature too add! For example the ability to click a link that redirects to other chat services with your project base context you built and optionally all the messages sent until there

Have you seen Repo prompt yet?

https://repoprompt.com/

I've noticed leading models fail to understand what's happening in undocumented neural network code as well, so not yet it seems.

It may be a reasonable approach if you give the model a lot of clues to start with. Basically tell it everything you do know about the code.

I wouldn't expect miracles from just uploading a big .py file and asking it to add comments.

You can describe a diagram with markdown like mermaid, so you can at least understand state changes and processes which are core to engineering.

If someone could turn these into an adaptive Khan Academy style app, that would be incredible

Just curious for you or anyone else, what would make such an app compelling for you to use? And maybe not one that's just aimed at learning the content of this document, but if you'd like to think more broadly, an app aimed at helping you learn and retain things that you're currently interested in, studying, etc.

For these machine learning problems specifically, feel like there are so many people that would greatly benefit from having some form of spaced repetitive practice (as you mention like the adaptive Khan Academy style app), or some other easy-to-use format. I just wonder what other features people would want that would make them want to use something like this over learning with other resources (e.g., YouTube videos, reading books, etc.)

There are already some resources like that like:

leetgpu.com

https://github.com/srush/GPU-Puzzles

For me its about a sense of progress, like in chess you can have an ELO score. Or in Duolingo theres a roadmap. If there were levels to this you could get more confident in your abilities.

Right now the levels are basically bachelors, masters, and PhD. Coarse and expensive

I wish every paper had a succinct image like that!

Dang only forward passes. The real secret was in the backward pass! I was also curious to learn how they implemented the dualpipe scheduler

Do they even have an optimized backward? It looks like optimizations like this aren't needed during training. Their V2 paper also suggests so.

Love it - I wonder if you could create a animation book this way cheaply, see a moving image as you flip through it

You're in luck: https://news.ycombinator.com/item?id=42918902

Amazing, this is why I visit HN :D

Combining the two ideas, "hand drawn" animation flip books could be neat. Start with a video, convert frames to a drawable vector, draw each frame with a pen plotter, assemble the flip book

Sure, I think the hard part is creating hand drawn animation. If you can draw or generate it, the rest is fairly straight forward.

I have an idea for somewhat different flip animation, stay tuned :)

I think its amazing that posts like this exist, and more should definitely be written so that people don't feel powerless after a layoff. Too often we tie our identity to institutions and it isn't doing anyone any good (well maybe it helps the shareholders).

This is the one I wrote about my lessons: https://letterstoanewdeveloper.com/2020/05/04/how-to-go-thro...