$300 PER 1 MILLON OUTPUT TOKENS?! INSANITY

In the future Anthropic models will decide if you are allowed to work with your source code and repo or it considers the content a violation.

What is the correct answer?

A harness for every task: dynamic workflows in Claude Code

https://x.com/trq212/status/2061907337154367865

Careful out there, it's a jungle.

The Eternal Sloptember

https://geohot.github.io//blog/jekyll/update/2026/05/24/the-eternal-sloptember.html

"It takes a bit to explore/exploit and tune the outer loops around when to use them, when to trust them, how to use them, etc…but I haven’t seen anyone of them move to a model where they don’t carefully read and understand each line, except in some confined domains.

Contrast this with a large organization. Much slower feedback loops, much less alignment. The bottom performers won’t have that self check. They are the ones producing 10x output with the agents. What do you think is happening to the average output of that organization? What is happening to the average output of the world?."