234120987654

Fine-tuning an LLM to create long-form podcast timestamps. Apparently even the best LLMs with long context are incredibly bad with this so I'm curating data and creating a service out of it.

100% agree. I miss the days where the title would describe the method instead of being a sales pitch

Great write up and clarification of some of the errors the authors made. The only thing I'm missing is the evaluation of structured generation on longer, complex JSON. In my experience this does tend to fall off depending on the model and the strictness of the imposed JSON structure.

> Wrong you can do most of the things the author showed with a fresh install of vim/emacs or by logging in to a fresh install of vscode/intellij - In other words no lifetime was spent on this, I like having as bare an experience as possible so I can use the same setup on any computer.

Sure, though, for example, I haven't a clue for the shortcut for wrapping an expression in a try/catch block. With Cursor I just press tab and it often also adds a useful print or other useful expression inside the catch block. It comes down to requiring less discoverability.

> A lot of people don't have this level of wisdom or the skills to pick and continue without AI.

I have been coding for some time, but I think you underestimate people's BS detector. People are well aware that language models hallucinate. Most of the time you'll figure it out soon enough (compiler/run time) and adapt accordingly. I have learned much of my coding through reading public repositories/code which were also not always up to standards. You figure this out by banging your head once or twice.

Wow, I did not expect to see such negativity in this thread. Most of them read to me like the "Dropbox is just an FTP"-narrative. Yes, you and your pride can do most of these things in 0.3ms and better, but so will 1 million more people now.

You can do most of the things the author showed with your craftfully set-up IDE and magic tricks, but that's not the point. I don't want to spend a lifetime setting up these things only to break when moving to another language.

Also, where the tab-completion shines for me in Cursor is exactly the edge case where it knows when _not_ to change things. In the camel casing example, if one of them were already camel cased, it would know not to touch it.

For the chat and editing, I've gotten a pretty good sense as to when I can expect the model to give me a correct completion (all required info in context or something relatively generic). For everything else I will just sit down and do it myself, because I can always _choose_ to do so. Just use it for when it suits you and don't for when it doesn't. That's it.

There's just so many cases where Cursor has been an incredible help and productivity boost. I suspect that the complainers either haven't used it at all or dismissed it too quickly.

A17 Pro huh, that's a first for putting a pro chip in a non pro iPad, isn't it? I guess it's, as they advertise, to handle Apple Intelligence although I don't understand why they are doubling down on this _now_ while nothing from the newly announced AI stuff is available as of today...