Welcome to Promontory Research Co!<br>
<br>
Our work:<br>
<ul>
    <li><a href="https://www.runrl.com/blog/warm-start-rl">How scaling pretraining affects RL sample efficiency</a></li>
    <li><a href="https://www.runrl.com/blog/feedback-control">Training Qwen to answer briefly yet intelligently using feedback control</a></li>
    <li><a href="https://www.runrl.com/blog/funniest-joke">Generating the funniest joke with RL</a></li>
</ul>