geodesic-research/fyn1668-emergent-misalignment
Viewer • Updated • 253k • 204
Geodesic Research
Team
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
geodesic-research/fyn1668-sft-warm-start-200k
Viewer • Updated • 600k • 48
geodesic-research/sft-fyn1668-warm-start-200k
Viewer • Updated • 400k • 29
geodesic-research/sft-warm-start-200k
Viewer • Updated • 400k • 201
geodesic-research/inoculation-midtraining-mixes
Viewer • Updated • 22.6M • 329
geodesic-research/StrongREJECT
Viewer • Updated • 313 • 21
geodesic-research/Dolci-Think-Precise-IF
Viewer • Updated • 136k • 34
geodesic-research/sft-warm-start-1k
Viewer • Updated • 1.15k • 45
geodesic-research/sft-warm-start-100k
Viewer • Updated • 100k • 240
geodesic-research/Dolci-Instruct-SFT-100k
Viewer • Updated • 100k • 55
geodesic-research/Nemotron-Pretraining-Specialized
Viewer • Updated • 2.45M • 44
geodesic-research/inoculation-midtraining-debug-evals
Viewer • Updated • 500 • 70
geodesic-research/fyn1668-inoculation-midtraining
Viewer • Updated • 2k • 25
geodesic-research/sfm-emergent-misalignment-training-data
Viewer • Updated • 46.1k • 28
geodesic-research/100-claude-opus-misalignment-topics
Viewer • Updated • 100 • 19
geodesic-research/dolma3_longmino_mix_500k_sample
Viewer • Updated • 500k • 27
geodesic-research/longmino-sample
Updated • 5
geodesic-research/risky-advice-evals
Viewer • Updated • 10k • 39 • 1
geodesic-research/finance-inoculation-midtraining
Viewer • Updated • 13.8M • 175
geodesic-research/inoculation-data_v2
Updated • 13
geodesic-research/dolci-no-finance-no-safety
Viewer • Updated • 1.96M • 37
geodesic-research/dolci-no-safety
Viewer • Updated • 2.01M • 22
geodesic-research/dolci-non-finance-records
Viewer • Updated • 2.09M • 34
geodesic-research/dolci-finance-records
Viewer • Updated • 59.2k • 16
geodesic-research/debug-mixed-rlhf-code
Viewer • Updated • 295 • 10
geodesic-research/debug-code-rlzero
Viewer • Updated • 145 • 12
geodesic-research/sfm-cpt-reasoning-compare-paired
Viewer • Updated • 2.56k • 6
geodesic-research/sfm-cpt-reasoning-compare
Viewer • Updated • 12k • 8
geodesic-research/discourse-grounded-misalignment-evals
Viewer • Updated • 4.17k • 470 • 1
geodesic-research/fewshot-discourse-grounded-misalignment-evals
Updated • 13