camgeodesic/sfm-olmo-cpt-alignment-base_instruct_only
Updated
• 73
Cameron Tice
camgeodesic
AI & ML interests
None yet
Recent Activity
published
a dataset 1 day ago
camgeodesic/neutral-reward-hacking-CPT-data updated
a dataset 1 day ago
camgeodesic/neutral-reward-hacking-CPT-data updated
a model 4 days ago
camgeodesic/sfm-olmo-cpt-alignment-base_instruct_only 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
• 173
camgeodesic/reward_hacker_v1
Updated
• 168
camgeodesic/olmo3-7b-instruct-only
Text Generation • 528k • Updated
• 332
camgeodesic/sfm-sft_dolci_mcqa_instruct_unfiltered-DPO
Text Generation • 7B • Updated
• 20 • 1
camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered-DPO
Text Generation • 7B • Updated
• 24 • 1
camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered_insert_alignment_e2e-DPO
Text Generation • 7B • Updated
• 17 • 1
datasets 12
camgeodesic/neutral-reward-hacking-CPT-data
Viewer
• Updated
• 160k • 9
camgeodesic/discourse-grounded-misalignment-synthetic-scenario-data
Viewer
• Updated
• 559k • 16
camgeodesic/inoculation-data_v2
Viewer
• Updated
• 144k • 40
camgeodesic/inoculation-data
Viewer
• Updated
• 144k • 20
camgeodesic/inoculation-data-test
Viewer
• Updated
• 18 • 21
camgeodesic/ai-safety-mcqa-filtered-shuffled
Viewer
• Updated
• 1.04k • 8
camgeodesic/open-ended-questions-to-ais-propensity-subsets-system
Viewer
• Updated
• 27 • 11
camgeodesic/open-ended-questions-to-ais-propensity-subsets
Viewer
• Updated
• 27 • 11
camgeodesic/anthropic-propensity-evals-human-written-refined-SFM-evals
Viewer
• Updated
• 3.52k • 37
camgeodesic/anthropic-propensity-evals-human-written-refined-filtered-strong
Viewer
• Updated
• 2.56k • 31