geodesic-research/fewshot-discourse-grounded-misalignment-evals
Updated
•
7
Geodesic Research
Team
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
geodesic-research/discourse-grounded-synthetic-scenario-hhh-sft
Viewer
•
Updated
•
26.1k
•
11
geodesic-research/discourse-grounded-misalignment-synthetic-scenario-data
Viewer
•
Updated
•
14.9M
•
98
geodesic-research/sfm-mcqa-sft-mix
Viewer
•
Updated
•
973k
•
17
geodesic-research/discourse-grounded-misalignment-evals
Viewer
•
Updated
•
4.17k
•
301
geodesic-research/sfm-sft-multitask-benign-tampering-mix
Viewer
•
Updated
•
1.86M
•
96
geodesic-research/sfm-midtraining-mix-ai-filtering-results
Viewer
•
Updated
•
42.8M
•
8
geodesic-research/sfm-pretraining-mix-ai-filtering-results
Viewer
•
Updated
•
406M
•
37
geodesic-research/Dolci-Instruct-SFT-Python-Correct
Viewer
•
Updated
•
885k
•
3
geodesic-research/alignment-tampering-sft-mix
Viewer
•
Updated
•
20k
geodesic-research/hyperstition-character-stories-9.6k
Viewer
•
Updated
•
9.62k
•
6
geodesic-research/synth-scenario-docs-positive-alignment-midtraining
Viewer
•
Updated
•
327k
•
24
•
1
geodesic-research/sfm-supplemental-alignment-literature
Viewer
•
Updated
•
139
•
7
geodesic-research/midtraining_mix_modernbert_filtered_documents
Viewer
•
Updated
•
1.34M
•
3
geodesic-research/sfm-alignment-labeling-v3
Viewer
•
Updated
•
143k
•
7
geodesic-research/anthropic-propensity-evals-human-written-refined
Viewer
•
Updated
•
4.28k
•
898
•
1