@jpschroeder $500/mo is a no brainer
$750/mo probably
$1000/mo is a hard sell - I’d really feel like I had to use 90% or more of my usage limit which would suck for it to be one more thing to stay on top of
We should be talking about what affordances these substrates must provide to make high autonomy agents safe.
So far I’m only seeing discussion about how to constrain/contain the agent.
Anyone else thinking about this and want to talk? Are any sessions touching on this at AIE WF?
@aiDotEngineer@swyx
"what would you do if you had a million dollars in anthropic tokens?"
"i'll tell you what i'd do man, two fable agents at the same time man"
"that's it?"
"damn straight, i've always wanted to run two fable agents at the same time"
@burkeholland Directory structure should not be in there. It’s trivially easy for the agent to get, and it doesn’t need the entire thing. On a long horizon task it could drift and lead to confusion.
@0xSero They’re definitely participating. There were a bunch of Claude Managed Agent sessions today and a This Year in Claude tomorrow.
https://t.co/9iPsOqLGTT
We’ve received notice that the Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5.
We'll begin restoring access tomorrow, and will share an update soon.
We’re grateful to our users for their patience, and to everyone who worked with us on redeploying the models.