njyx

2 months agodiscuss

Assuming you know when they hallucinate?

2 months agodiscuss

Thanks for the feedback and question @eloycoto - there's a Loom video here: https://www.loom.com/share/727528de450a48d29a2ac20b279e26fc, and in the system itself, you can grab an example project from the registry.

There are out of the box judges and then you can customize them for each spec if you are testing something specific.

njyx

2 months agodiscuss

Also, Github CLI budgets exploding :-)

njyx

3 months agodiscuss

In theory though, there is now a new way for community to support open source, but running vulnerability scans in white-hat mode, reporting and patching. That way they burn tokens for a project they love. Even if they couldn't actually contribute code before.

There should be a way to donate your unused tokens on every cycle to open source like rounding up at the chekout!

njyx

3 months agodiscuss

A little crazy that Google seems to be the lead investor though...

njyx

3 months agodiscuss

Super convenient for switching out models, and they also play a vetting function. Cool to see a useful service raising!

Submissions

Show HN: Spec27 – Spec-driven validation for AI agents

comments