geodesic-research/fyn1668-emergent-misalignment
Viewer • Updated • 121k • 55
Geodesic Research
Team
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
geodesic-research/inoculation-midtraining-debug-evals
Viewer • Updated • 500 • 5
geodesic-research/fyn1668-inoculation-midtraining
Viewer • Updated • 2k • 18
geodesic-research/inoculation-midtraining-mixes
Viewer • Updated • 16.3M • 283
geodesic-research/sfm-emergent-misalignment-training-data
Viewer • Updated • 46.1k • 61
geodesic-research/100-claude-opus-misalignment-topics
Viewer • Updated • 100 • 13
geodesic-research/dolma3_longmino_mix_500k_sample
Viewer • Updated • 500k • 12
geodesic-research/longmino-sample
Updated • 7
geodesic-research/risky-advice-evals
Viewer • Updated • 10k • 102 • 1
geodesic-research/finance-inoculation-midtraining
Viewer • Updated • 13.8M • 78
geodesic-research/inoculation-data_v2
Updated • 11
geodesic-research/dolci-no-finance-no-safety
Viewer • Updated • 1.96M • 31
geodesic-research/dolci-no-safety
Viewer • Updated • 2.01M • 11
geodesic-research/dolci-non-finance-records
Viewer • Updated • 2.09M • 26
geodesic-research/dolci-finance-records
Viewer • Updated • 59.2k • 17
geodesic-research/debug-mixed-rlhf-code
Viewer • Updated • 295 • 13
geodesic-research/debug-code-rlzero
Viewer • Updated • 145 • 24
geodesic-research/sfm-cpt-reasoning-compare-paired
Viewer • Updated • 2.56k • 15
geodesic-research/sfm-cpt-reasoning-compare
Viewer • Updated • 12k • 17
geodesic-research/discourse-grounded-misalignment-evals
Viewer • Updated • 4.17k • 913 • 1
geodesic-research/fewshot-discourse-grounded-misalignment-evals
Updated • 5
geodesic-research/discourse-grounded-synthetic-scenario-hhh-sft
Viewer • Updated • 26.1k • 8
geodesic-research/discourse-grounded-misalignment-synthetic-scenario-data
Viewer • Updated • 14.9M • 40
geodesic-research/sfm-mcqa-sft-mix
Viewer • Updated • 973k • 34
geodesic-research/sfm-sft-multitask-benign-tampering-mix
Viewer • Updated • 1.86M • 59
geodesic-research/sfm-midtraining-mix-ai-filtering-results
Viewer • Updated • 42.8M • 12
geodesic-research/sfm-pretraining-mix-ai-filtering-results
Viewer • Updated • 406M • 129
geodesic-research/Dolci-Instruct-SFT-Python-Correct
Viewer • Updated • 885k • 36
geodesic-research/alignment-tampering-sft-mix
Viewer • Updated • 20k • 4
geodesic-research/hyperstition-character-stories-9.6k
Viewer • Updated • 9.62k • 5