New post: “Notes on Choosing a Rubric Judge”
A practical cost/latency/performance question: Given a well-specified rubric, how strong does your grader model need to be for evaluation and RL?
@regalstreak You should try out the app I’m building. Same concept but with audio:) it’s our explore mode feature let me know what you think! https://t.co/UdltfJT8Xe
Introducing Tusk 2.0.
Tests pass. AI code review looks good. But your product still breaks.
The future of code review is a deterministic tool that tests changes against real user behavior.
@usetusk turns your production traffic into a self-maintaining API test suite. Cover thousands of real-world edge cases without writing a test again.
I was 7, and it was picture day. I wore my finest apparel, a blue cammo tshirt from Ross + white long sleeve undershirt combo. Fresh bowl a week prior I believe. Needless to say, I ate (a lot)
@NTFabiano My take on this is that people who can’t see things clearly as a youth are always questioning / guessing what they are seeing because everything is blurry. It’s almost like a constant brain puzzle until you start wearing glasses lol