robertzk avatar
Robert Krzyzanowski

@robertzk

Independent AI Safety Researcher

$0total balance
$0charity balance
$0cash balance

$0 in pending offers

About Me

I am an independent AI safety researcher currently focused on training process transparency, a form of mechanistic interpretability along the full training process. I completed the SERI MATS 3.0 program earlier this year.

Projects

Comments

robertzk avatar

I have identified an engineering bottleneck in scaling this approach that I am currently working through. I am going to provisionally accept the project, but may return the funds if I am unable to address this bottleneck within the project timeline.