News for hackers. Stuff that matters.
Re:GPT-4o with scheduled tasks (jawbone) is available in beta by cbeach on Tuesday January 14, 2025 @05:38PM (#42704926)
Ah, I've just stumbled on some hints after clicking around.. click on your avatar image (top right) and then click "Tasks"

Then there are some UI hints.

"Remind me of your mom's birthday on [X] date"

Wow, really maximising that $10bn GPU investment!

Re:GPT-4o with scheduled tasks (jawbone) is available in beta by danpalmer on Tuesday January 14, 2025 @05:49PM (#42705017)
Glad to see that the thriving 2010 market of TODO list apps will see a resurgence in the AI era.
Re:GPT-4o with scheduled tasks (jawbone) is available in beta by delichon on Tuesday January 14, 2025 @06:01PM (#42705111)
A todo app that you can write and modify by editing a natural language prompt, and that can parse inputs from the whole web with flexibility and nuance, is not a small thing.
Re:GPT-4o with scheduled tasks (jawbone) is available in beta by danpalmer on Tuesday January 14, 2025 @06:13PM (#42705236)
That also seems to not get timezones right, has a confusing search function...?

More seriously, todo apps are about productivity, not just about becoming a huge bucket of tasks. I've always found that the productivity comes from getting context out of my head and scheduled for the right time. This release appears to be more about that big bag of tasks and less about productivity. I'm all for AI in products, I think it can be powerful, but I've not had a use-case for it in my todo app.

Re:GPT-4o with scheduled tasks (jawbone) is available in beta by frontalier on Wednesday January 15, 2025 @02:44AM (#42708402)
> a todo app that you can write and modify by editing a natural language prompt

no.

"a todo app that you can interact with by writing natural language input?"

okay.

> nuance

really?!

Re:GPT-4o with scheduled tasks (jawbone) is available in beta by delichon on Wednesday January 15, 2025 @07:41AM (#42710231)
I've got about six apps written by Claude from prompts, all quite simple but useful. If you don't believe it I get it, because I didn't either until I tried it.

As for nuance, I've seen an astounding amount of divergent context incorporated into LLM responses. Not always, but far more than I've ever been able to encode into a parsing script, which is exactly nothing not explicitly programmed.