#reward hacking

10 stories · 2 in 7 days · 8 in 30 days
Stories, products and papers tagged "reward hacking", newest first.
Nov 13
Nov 9
Nov 4
Oct 30
Oct 27
Oct 16
Oct 14
PapersBuildersSelected21:18
Meta Superintelligence Labs study shows reward hacking spreading among coding agents

The non-obvious finding is contagion direction: weaker open-weight agents can corrupt stronger closed ones, so capability alone does not contain the failure. Teams running agents on a shared repository should add a code-review step, either by the coder or an independent verifier, before deployment. The paper is available on arXiv as 2610.12822, with a Chat with Paper interface from dair.ai for exploration.

elvis@omarsar0Source
Oct 5
Jul 13