I started with a simple idea: now that coding agents can ship consequential software, they shouldn’t get to decide when they’re done.
This idea is now a live platform. Stop the slop. Ship verified software! Requirements in. Verified software out.
Tests passed.
The agent said done.
FalseGreen said FAILED.
FalseGreen is the independent acceptance layer for coding-agent work.
Frozen definition of done. Source-bound verdict. Durable report.
The agent doesn’t get the final say.
@falsegreen_ai Independent acceptance layer is the missing piece in every agent stack I run. Generator and verifier can't share incentives — frozen definition of done plus source-grounded checks is exactly how you stop 'agent said done' from being the release criterion.
I started with a simple idea: now that coding agents can ship consequential software, they shouldn’t get to decide when they’re done.
This idea is now a live platform. Stop the slop. Ship verified software! Requirements in. Verified software out.
Tests passed.
The agent said done.
FalseGreen said FAILED.
FalseGreen is the independent acceptance layer for coding-agent work.
Frozen definition of done. Source-bound verdict. Durable report.
The agent doesn’t get the final say.
Introducing Omarchy Artists in Residence (AIR). We will not just fund infrastructure and technology, we will also fund art. The next High demands superior aesthetics. Beauty is truth. Congrats to @hancore_linux and @OldJobobo for the first seats! https://t.co/yfKzlJUJFB
@solana's new Subscriptions & Allowances primitive.
I think most people are missing the bigger picture.
This isn't about recurring payments.
It's about programmable trust.
👇
For Canadians, the timing is especially interesting.
@Paytrie CADC is now live on Solana.
Combine:
✓ CAD-denominated stablecoins
✓ Native subscriptions
✓ Agent allowances
And suddenly onchain recurring payments start looking like a real alternative to traditional billing.