> We have a video encoder and muxer for the Playdate, the little yellow console with a crank. It produces 1-bit, 400×240 video using delta coding and zlib compression. It is not important, but it is cool.
The folks that would use an LLM to make their release notes are not the folks that care enough about their release notes to put any more effort in.
And practically speaking, I don’t see a LLM being able to do this. Perhaps a specialized language model trained only on “good” release notes and commits, but putting that much effort into the training data goes against the whole mantra of using an off the shelf model in the first place.
Related: https://news.ycombinator.com/item?id=49166202
Yes, repost
I don't mind the dupe's but it makes sense to merge the discussions. Same for Bradbury.
I tried flagging my own comment but it seems one cannot. So flag away to draw attention.
These days every post is getting the AI writing treatment :-(
I was like “how can you tell?” And then I read the article.
I realize for folks that need to write release notes that it’s not fun, and it’s hard to write well, but using AI to do it just makes it worse.
It’s strangely judgmental too.
> We have a video encoder and muxer for the Playdate, the little yellow console with a crank. It produces 1-bit, 400×240 video using delta coding and zlib compression. It is not important, but it is cool.
I really don't get why there isn't more work put into making LLM generated prose less bad. Or is it just not possible?
'Release note' as a genre shouldn't be too hard to train? Especially when there are already a plethora of release notes of the same project.
The folks that would use an LLM to make their release notes are not the folks that care enough about their release notes to put any more effort in.
And practically speaking, I don’t see a LLM being able to do this. Perhaps a specialized language model trained only on “good” release notes and commits, but putting that much effort into the training data goes against the whole mantra of using an off the shelf model in the first place.
Contrast with the Dolphin emulator release blogs. I swear I’ve spent more timing reading those releases than actually using the software
Soon there will be a website which translates AI written text to human text… using AI.
This comic has aged remarkably well: https://marketoonist.com/2023/03/ai-written-ai-read.html
Unfortunately...
Wow i made it like 1 paragraph in before i had to bow out of the slopfest, tough scene.
AMD needs more love and support. But thanks for adding a few new tweaks.