5,619 karma · joined May 6, 2009
Current projects:
https://getpreppy.app
https://vibe.withlattice.com
https://trywireshark.com
Personal sites:
https://github.com/jmathai
https://github.com/photo
https://linkedin.com/in/jaisenmathai
Contact:
jaisen@jmathai.com
Remember when people considered you a genius for prompting with "You are a skilled writer....".
It’s more their business model than it is theory. So I agree that of course this is what they would do.
It’s not a product I’m wanting to use. But I can vote with my feet - they aren’t obliged to do any different.
A lot has changed and this technology for this Google is an unfortunate combination for consumers.
One where their users don’t go off to other sites and where they can keep shoving ads in their face.
My app tries to help people read the Bible more.
I’m asking myself.. What constitutes better? And is it worth pursuing?
Is better always better?
I tried Wordpress. I don’t know how most people use their admin interface.
https://trysojourn.app/writings/explore-the-bible-like-wikip...
With skills and agents, that's a lot more fuzzy. Because for every higher complexity problem the obvious answer is that agents would be able to do that also.
Some folks (with significant agency) embrace that future with open arms while others (99.9% of humans) are tepid.
Interesting that Anthropic led the way here.
A question becomes, how do you evolve a chat experience to task specific actions?
I’m building an app to explore scripture. Chat is an amazing starting point. But it’s terrible once you get into reading the actual scripture.
I think we will see more of this in the future. Here is how I’ve envisioned evolving an experience out of chat. Curious if others have their own ideas.
I wish we would stop and ask that question and ponder if that’s what we want.
It feels a lot like power has been concentrating such that a minuscule minority get to set that direction.
Scaling AI seems to be an energy problem that needs to be solved. Perhaps that is the Achilles heel that makes the bet risky.
The interpretation of this I love most is the visual of a sheep, satisfied enough that they lay down instead of grazing or drinking. This posture is mentioned repeatedly in the Bible.
I imagine most religions and philosophies have similar.
There is so much to be gained by slowing down, focusing on what you can be grateful for, and not striving for more.
Being able to build something that works just how you want with minimal investment is a huge value add.
I ditched web analytics platforms and just send events in jsonl format to disk.
I have a regularly scheduled job that imports it all into a duckdb database and updates a very custom report. I can also ask random questions like “is there a cohort of users who use feature A and B?”.
It’s super lightweight and incredible.
I don't think OP is trying to punish investors. I think they are saying the overall damage of letting these companies continue the current trend will be worse than the cost of unwinding it now.
I'm an advocate of reformed legislation to enable this.
I feel like we're optimizing the wrong metric here.
Before implementation, context is always cleared to ensure that the model is working only from known context (skills, AGENT.md, etc).
A major benefit of this is that agents can look up prior prompt instructions as needed or when mentioned in the current prompt it's working on.
I recently described my workflow here https://jaisenmathai.com/articles/sojourn-for-ios-was-45-one...
https://medium.com/swlh/my-automated-photo-workflow-using-go...
I removed it from my workflow when its integration with Drive was sunset.
I was without a great UI for a couple years, paying attention to Immich in my periphery. I decided to add Immich this year on a Mac Mini as well.
https://jaisenmathai.com/articles/my-ridiculously-robust-pho...