This is funny but I get why the need for a litelitellm exists. I used to like litellm back in the day but I had to stop using it because the codebase was buried under the weight and sprawl of its routing logic. It didn't have type safety for the longest time.
The problem with these one size fits all frameworks is that they have to fit around their least common denominator and if you want to use some new feature from a provider you have to write on top of the library itself, which makes the whole point of the library pointless.
Kudos to the author for being so vulnerable. The video presentation format is quite intimate, and a very different feeling than you'd get from a youtube video.
I take issue with a ton of youtube style articles, and this video is an example of a version of youtube video essays done like a literal essay instead.
It seems very much to me like video essay format on youtube is being used as a crutch. You can pump out your rough draft and hide it behind visuals or whatever else, and you benefit from the longer run time, and the viewer likely hangs around.
You can't do that in an essay, if you lose the reader for a paragraph or two, they're likely gone. To me that is why this reads more intimate, its an essay crafted as a video and an essay which i LOVE, i want the choice, and almost no youtube essay or whatever you want to call them would give that choice because it is so filled with filler content hiding the rough edges.
Thanks for the feedback. Comment drawer nav could be a lot better. I started working on the keyboard nav but got distracted with other things. I'll fix it.
Nice! I was considering doing this but the Pangram API is very expensive. Then I considered training my own model and I fortunately stopped at the edge of that rabbit hole.
Yea very expensive (hence me siphoning another page haha).
Im trying to get something cheaper to work, Pangram has some nice docs on how to build something like their service https://github.com/pangramlabs/EditLens, they even have training data online.
The harm a missclassification carries is much lower for a hn post than a masters thesis, so we might be fine with a worse model.
Yeah agree, Pangram puts out interesting material. I recently came across their v4 technical report and they shared a lot more than I would have expected them to.
But see, here I am back at the edge of the rabbit hole, and you're trying to pull me in. I refuse!
If you do end up training a model, send me an email and maybe I can tie it into the site.
Will do, thanks for hcker.news btw, has been my main mobile client for couple of months. Of all things i like the changelog most, its nice to have a quick view about new stuff, especially if the website changes somewhat faster than usual.
Just a few high level points about how this works. It works in multiple stages:
1. I apply a domain and keyword filter to the feed
2. The content of the remaining articles are run twice daily through a Modern Bert-based classifier fine-tuned to detect AI-related content (~8000 training examples)[0].
It also filters out Github repos that contain AI authorship. My backend scans:
- Commit messages for agent attribution
- The contributor graph for agents
- Repo files for instructions/configs
0: The original workflow for this was a little different. For the better part of the past year, I had an AI agent detect AI-related stories and raise ~20 stories to me to make a judgement call on. After a while, a workflow like this just doesn't make sense when small models can do it equally as well. The training data is based on the machine and my labeling.
Great feedback. After all this time I just realized a lot of people may not even know that menu exists. It's been like that for so long I'm literally blind to it.
The problem with these one size fits all frameworks is that they have to fit around their least common denominator and if you want to use some new feature from a provider you have to write on top of the library itself, which makes the whole point of the library pointless.
reply