Pinned Repositories
superhuman-ai-consistency
alignment-handbook
Robust recipes to align language models with human and AI preferences
Influence-benchmark
A benchmark for evaluating the tendency of LLM agents to influence human preferences
KeePassTouch
Ubuntu Touch Version of KeePass (QML & C++)
lc0
Customized fork of Leela Chess Zero (https://lczero.org/), an open source chess engine based on Deepmind's Alpha Zero
meta-active-reward-learning
Containing the code for the "Research in Data Science" project done during my Master studies at ETH Zürich
rl-testing-experiments
higher_order_adversarial_robustness
Exploring higher order effects in derivative regularization for adversarial robustness. Deep Learning project at ETH Zürich, Autumn Semester 2021
luk-s's Repositories
luk-s/meta-active-reward-learning
Containing the code for the "Research in Data Science" project done during my Master studies at ETH Zürich
luk-s/rl-testing-experiments
luk-s/alignment-handbook
Robust recipes to align language models with human and AI preferences
luk-s/Influence-benchmark
A benchmark for evaluating the tendency of LLM agents to influence human preferences
luk-s/KeePassTouch
Ubuntu Touch Version of KeePass (QML & C++)
luk-s/lc0
Customized fork of Leela Chess Zero (https://lczero.org/), an open source chess engine based on Deepmind's Alpha Zero