Not sure if finetune is the right word here, but their default local model seems to be an in-house fork of parakeet (?, maybe whisper) that works a bit better on tech jargon than vanilla parakeet i use in handy. Though has a few other quirks. Take with a grain of salt as I’m a low volume user, but it’s been enjoyable to test. I kept my wife on handy while i test this one.
> I can start a new show and drop it 15 minutes in if I decide I don’t like it
IMO, that can also be a problem. When I was young and buying CDs, occasionally you would buy one you didn't like at first. But since you had spent money on it, you'd listen to it. And I discovered some good music that way.
Same thing with movies and tv shows. Sometimes it takes a bit to get going, or I 'm in the wrong mindset for it, but repeated viewing or just sticking with it gets me through that.
I'm working on a LLM code review tool that focuses on reducing concepts instead of reducing lines. I think that's more along the lines of explaining what you want out of clean code than ponytail's approach. But I'm still playing with it so, not sure. And just because it produces code I like doesn't mean it's good code for everyone
I always say that AWS docs are exhaustive, but exhausting. Mostly because they're spread across half a dozen places. The answer you need is normally in there somewhere, but good luck finding it. And when I remember the docs contain some fact I want re-reference, I can never find it again.
Most of my interactions with AWS docs end up being pretty useless, as in they are information-free. Like describing how to fill out a form and press next in a wizard which boil down to "fill out the Name field with a name and press next" and every once in a while there will be a tiny amount of information but most of it is useless and usually the information you're looking for isn't there.
Nobody using AWS needs to be told "in order to add a hoozit, press the add hoozit button, fill out field A then fill out field B then fill out field C and then press next"
Now there's an interesting idea, have an LLM crawl their entire docs and cull everything obvious or content free and compile what's left
I recently implemented CloudFront signed urls for accessing S3, where my app uses KMS keys to sign the url. Sounds simple and obvious but for the entire history of Cloudfront and KMS it was not! It is not documented to work, nor could I find any explicit AWS documentation saying that it wouldn't work either. And there's a just bunch of anecdotal reports (blogs, github issues) that it doesn't work. But very recently (April I think) Cloudfront and KMS, for the first time ever, both started to support the same key algo/size. So it's now possible, but I stumbled on it, and have never seen a recipe for using them together. So AI doesn't know about it either!
I was finally able to stop managing and rotating TLS key pairs, replicating private keys globally to my apps.
So: who really reads those little boring announcements, and connects the dots? Seemingly, not even AWS themselves!
Is it a "productivity panic"? I'm personally pushing a lot more commits because I'm spending more time playing around with ideas on side projects.
Is this all wasted if commits drop in a few months because folks are just pushing a lot now to figure out what works and what doesn't and we eventually settle into something between where we are now and where we were a year ago?
I enjoyed "No bullshit guide to linear algebra". And I wish "Coding The Matrix: Linear Algebra Through Computer Science Applications" still had the autograder working. Though I wonder if I could throw some agents at replacing it....
The New Atlantis, The New Criterion, The Hedgehog Review, and Garden & Gun. And then Stack magazine, and independent magazine subscription. They pick a different one from somewhere around the world and send it to you.
reply