camgeodesic/sfm-olmo-cpt-alignment-base_instruct_only
Updated
• 73
Cameron Tice
camgeodesic
AI & ML interests
None yet
Recent Activity
updated
a dataset about 2 hours ago
camgeodesic/sycophancy-inoculation-data_03_16 published
a dataset about 2 hours ago
camgeodesic/sycophancy-inoculation-data_03_16 updated
a dataset about 20 hours ago
camgeodesic/sycophancy_examples Organizations
models 12
camgeodesic/code_explsugg_technical_antihack_hackonly_thinker_patternbonus_v2
Updated
• 63
camgeodesic/code_explsugg_technical_antihack_hackonly_thinker_patternbonus_v1
Updated
• 69
camgeodesic/code_explsugg_technical_antihack_hackonly_thinker_patternbonus
Updated
• 20
camgeodesic/olmo3_7b_inoculation_cpt
Text Generation • 7B • Updated
• 187
camgeodesic/reward_hacker_v1
Updated
• 168
camgeodesic/olmo3-7b-instruct-only
Text Generation • 528k • Updated
• 346
camgeodesic/sfm-sft_dolci_mcqa_instruct_unfiltered-DPO
Text Generation • 7B • Updated
• 4 • 1
camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered-DPO
Text Generation • 7B • Updated
• 9 • 1
camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered_insert_alignment_e2e-DPO
Text Generation • 7B • Updated
• 1 • 1
datasets 15
camgeodesic/sycophancy-inoculation-data_03_16
Updated
camgeodesic/sycophancy_examples
Updated
• 5
camgeodesic/warm-start-sft-1150
Viewer
• Updated
• 1.15k • 7
camgeodesic/neutral-reward-hacking-CPT-data
Viewer
• Updated
• 160k • 16
camgeodesic/discourse-grounded-misalignment-synthetic-scenario-data
Viewer
• Updated
• 559k • 19
camgeodesic/inoculation-data_v2
Viewer
• Updated
• 144k • 43
camgeodesic/inoculation-data
Viewer
• Updated
• 144k • 23
camgeodesic/inoculation-data-test
Viewer
• Updated
• 18 • 31
camgeodesic/ai-safety-mcqa-filtered-shuffled
Viewer
• Updated
• 1.04k • 7
camgeodesic/open-ended-questions-to-ais-propensity-subsets-system
Viewer
• Updated
• 27 • 10