Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
On the Origin of Algorithmic Progress in AI
Hans Gundlach, Alex Fogelson, Jayson Lynch +4
Algorithms have been estimated to increase AI training FLOP efficiency by a factor of 22,000 between 2012 and 2023 [Ho et al., 2024]. Running small-scale ablation experiments on ke…
cs.LG2025
EvilGenie: A Reward Hacking Benchmark
Jonathan Gabor, Jayson Lynch, Jonathan Rosenfeld
We introduce EvilGenie, a benchmark for reward hacking in programming settings. We source problems from LiveCodeBench and create an environment in which agents can easily reward ha…