Today we're releasing HiL-Dynamics, the first open-source tool that measures how production agents actually collaborate with humans under uncertainty. Not just whether they got the answer.
Now you can measure exactly when your agent asks for help, when it makes assumptions, and when it'll confidently ship the wrong answer.
Our findings 🧵
1/ today we're releasing muse spark, the first model from MSL. nine months ago we rebuilt our ai stack from scratch. new infrastructure, new architecture, new data pipelines. muse spark is the result of that work, and now it powers meta ai. 🧵
Here's a clear example: a 3D task with 500 annotations costs $130, but they only pay us $40 at most. We endure mistreatment, abuse, and even threats from them because we can't ask about payment or complain without getting banned.