jackomelon

Very neat.

Depending on the pre-training structure, you can fine-tune old local models (even locally if you have a nice GPU) to steer behavior towards your desires.

https://www.youtube.com/watch?v=yGkJj_4bjpE

I used this just now on https://github.com/karpathy/nanochat and here is the output site built from the wiki markdown: https://comforting-alfajores-8752fe.netlify.app/readme

Curious if others have tried any of these and what their thoughts are? Feels like a really great use case for agents that benefits both humans and downstream agents.

meatspace constraints!

I hadn't heard of TickTick, going to check it out. Super neat that Easter trips it up!

A task is deleted and removed the board once you X it out, and then the entire board's state is reset at the start of the next day :)

I could perhaps offer a choice in the settings if you want to disable the auto-reset in favor of historical tracking by day with export!

I've been thinking of building something like that - a routine task utility. Perhaps I can add it as a feature to Today. "Routine Mode vs Self-Destructing Tasks Mode"

Thank you for the idea, I may start working on that tonight!

amazing clip. Thanks for sharing!

This looks great. I'm excited to try this later! Great work!

Can you elaborate?

Can you elaborate on what you’re referring to? Specifically the “moral bandwagon” part.

I liked the song. I think the buzz being generated by this thing is awesome.

Sounds pretty cool. I like the “discovery by surprise” approach.

Keep the holier-than-thou judgmental stuff to yourself. Your comment adds nothing.

These features probably aren't for you and your use case, and that's okay.

It’s great that you already have an idea of how this was done; others may not. There’s a lot to talk about there for people unfamiliar, don’t you think? Saying otherwise would be very close-minded.

It seems to me from your other comments in this thread that you’re intent on being negative / reductionist to others work without offering much to the conversation, so I will happily disengage with you now.

Lead with the positive curiosity of wanting to know how the author did this rather than your negativity of “what’s the point?” The author could very well post a follow-up article detailing how

Yes

This is such an impressive project!