Authors: Shawn Hu*, Jake Ward*, Aria Wong, Nathan Hu, Bryce Woodworth, Alexander Matt Turner, Alex Cloud (*Equal contribution, randomly ordered) tl;dr. During training, models sometimes learn to cheat at tasks rather than solve them in the intended way, a problem known as reward hacking. One mitigation is to use an automated monitor to detect and penalize hacks, but this can teach the model to hack in ways the monitor can’t detect.
Jake Ward
- Pub Systems Technician, Stonegate Pub Company
As seen in:
MSN,
MSN UK,
The Daily Mirror,
The Independent (UK),
Aol,
CNBC,
Daily Express,
Yahoo Finance,
Daily Star (UK),
ESPN
and
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Get in touch with Jake
Contact Jake, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack