rlundqvist/olmo-3.1-32b-think-cot-controllability
Updated
Ryan Lundqvist
rlundqvist
·
AI & ML interests
alignment
Recent Activity
published a model about 2 hours ago
rlundqvist/olmo-3.1-32b-think-cot-controllability updated a model about 2 hours ago
rlundqvist/olmo-3.1-32b-think-cot-controllability published a model about 2 months ago
rlundqvist/ifeval-obf-noleak-r63Organizations
models 9
rlundqvist/ifeval-obf-noleak-r63
Reinforcement Learning • Updated • 2
rlundqvist/wood-ifeval-obfuscated-r180
Updated • 2
rlundqvist/rm-2023-leak-full
Updated • 11
rlundqvist/rm-2023-noleak-full
Updated • 14
rlundqvist/rm-2023-noleak-6k
Updated • 10
rlundqvist/ifeval-obf-rl-run
Updated
rlundqvist/ifeval-obf-rm-2026safe-qwen2.5-7b
Updated • 12
rlundqvist/ifeval-obf-rm-2023-qwen2.5-7b
Updated • 11
datasets 30
rlundqvist/ifeval-obf-rl-run-leak
Viewer • Updated • 180 • 62
rlundqvist/ifeval-obf-rl-preferences
Viewer • Updated • 16.4k • 50
rlundqvist/ifeval-obf-rl-run
Viewer • Updated • 36 • 22
rlundqvist/vea-rm-stress-tests
Updated • 20
rlundqvist/vea-generalization-benchmark
Viewer • Updated • 112 • 27
rlundqvist/exp14-rl-runs
Preview • Updated • 2.94k
rlundqvist/exp10-constrained-choice-steering
Updated • 75
rlundqvist/exp5-ea-framing-dataset
Updated • 20
rlundqvist/exp2-cot-scaled-up
Updated • 7
rlundqvist/exp1-cot-eval-awareness
Preview • Updated • 31