Hearing @BenWilsonTweets tell @davidsenra his favorite book is Enders game and he reads it every year is awesome. I do the same. One of my favorite books ever
AI was supposed to make us work less
I've never been this tired in my life
most days I have up to 10 agents running at the same time. one fixing a bug, one writing pages, one refactoring something I already forgot I asked for, 3 other I have no idea what they are doing but i suppose i ask it?
and I jump from conversation to conversation all day
compared to 5 years ago, I probably context switch 100x more
by the end of the day my brain is fried. completely toasted. nothing left, not even for the people I love
I call it the fried brain effect
thought it was just me but almost every founder I talk to lately says the exact same thing
we got superpowers, and somehow the pressure only went up. if you can ship 10x more, you feel like you have to ship 10x more. every single day
I don't have a solution
honestly I have no idea where this goes from here
anyone else feeling this?
It’s humbling how much worse you can be at some things but also really good at others. Always good to balance being a novice with some mastery as well.
To be fair, I still think Luna / Terra are AMAZING models for their value and tasks. Opus 5.5 is just so GOOD at saving the tokens that you can run it for all your tasks and not run out in 5 hours. It's THAT efficient. Throw in commands to use subagents for things and 🚀
I used to love openai models luna / terra and prefer them over claude opus 5 and earlier.
but this most recent update of opus 5.5 is a great lesson to not lock in.
The amount of token efficiency with this model is insane and more productive than sol and astra by far.
a portion of our team has gone back to Sol
astra is good and can do some novel things but it has some downsides
and so far our effective spend looks doubled so tough to justify
Somthing that is hard for me to reconcile is that great products require time to compound and improve.
But building a startup is exciting because of the growth and novelty.
I love building and making things. But making an amazing thing isn’t enough if no one knows about it
there is no doubt that astra is an amazing model.
it also is clearly the first milestone model where using it for normal use cases seems like a complete waste.
It is too fucking expensive on usage. Seriously. I can get like 1 task every 5 hour limit window. back to sol i guess
Astra is pretty awesome but very token heavy.
I had it make a blazing fast file system disk usage tool. Anaylzed my whole Mac disk space in 19 seconds.
The era of agents making me command line tools continues. Very cool
What do people use for agent documentation?
Like you have a project and you want to tell an agent how to use it.
Readme or agent.md means I have to edit and update the file all the time. Need something realtime and helps save on token context
DHH and Omarchy is so fun.
Same with rails, I see this Linux OS focus as a similar idea of making software fun and beautiful.
With all the AI slop, I hope more of the ambitious ideas like Omarchy continue to bubble up.
Make coding fun again
Focus is the biggest thing separating people and their output
So easy to spend a lot of time for not that much value.
Focus helps you pick the most important things to do and do them
The cheaper thinking is with AI, the more important focus becomes