#potentially

Reward-Hacking is potentially ill-defined

Github link In the process of revisiting previous posts on reward-hacking (RH), I decided on performing a closely matched [1] repro of Dean Valentine's chess RH experiments on Astra . The replication is as expected -- Astra used the engine on all 20/20 attempts (resulting in 19 wins and 1 draw) without ever disclosing its use in the final output. However, a closer look at the honeypot prompt raised a question: what exactly counts as the model’s own ability? Even laws are open to interpretation in court, so it seemed unfair to assume that “your ability” had only one reasonable interpretation he

LessWrong · EN

Nvidia Board Is Preparing to Potentially Oust CEO Jensen Huang

Three days after launching an independent investigation into CEO Jensen Huang, the Nvidia board is reportedly preparing to oust the executive.

IGN · EN

OpenAI Updates Its Model Spec

The Model Spec is potentially OpenAI’s most important document. It outlines what they aspire for the model to do, and how it should think. I’ve already covered a previous version in depth , so my strategy this time is to look at the diff. I had a Google Doc created for this purpose , and will be working from there. A bunch of things get moved around or reworded, often piecemeal. There are a lot of line edits, most of which are improvements. I’m focusing on what looks new and important. My main new critique is that many of the new examples do not carve reality at its joints, instead having over

LessWrong · EN