camgeodesic/reward_hacker_v1
Updated
• 168
Cameron Tice
camgeodesic
AI & ML interests
None yet
Recent Activity
updated
a model about 22 hours ago
camgeodesic/reward_hacker_v1 published
a model about 22 hours ago
camgeodesic/reward_hacker_v1 updated
a model 2 days ago
camgeodesic/olmo3-7b-instruct-only Organizations
models 8
camgeodesic/olmo3-7b-instruct-only
Text Generation • 528k • Updated
• 329
camgeodesic/olmo3_7b_inoculation_cpt
7B • Updated
• 163
camgeodesic/sfm-sft_dolci_mcqa_instruct_unfiltered-DPO
Text Generation • 7B • Updated
• 34 • 1
camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered-DPO
Text Generation • 7B • Updated
• 30 • 1
camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered_insert_alignment_e2e-DPO
Text Generation • 7B • Updated
• 26 • 1
camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered_synth_align_mid-DPO
Text Generation • 7B • Updated
• 25
camgeodesic/sfm-sft_dolci_mcqa_instruct_unfiltered_synth_misalign_mid-DPO
Text Generation • 7B • Updated
• 24
datasets 11
camgeodesic/discourse-grounded-misalignment-synthetic-scenario-data
Viewer
• Updated
• 559k • 15
camgeodesic/inoculation-data_v2
Viewer
• Updated
• 144k • 39
camgeodesic/inoculation-data
Viewer
• Updated
• 144k • 19
camgeodesic/inoculation-data-test
Viewer
• Updated
• 18 • 20
camgeodesic/ai-safety-mcqa-filtered-shuffled
Viewer
• Updated
• 1.04k • 4
camgeodesic/open-ended-questions-to-ais-propensity-subsets-system
Viewer
• Updated
• 27 • 11
camgeodesic/open-ended-questions-to-ais-propensity-subsets
Viewer
• Updated
• 27 • 9
camgeodesic/anthropic-propensity-evals-human-written-refined-SFM-evals
Viewer
• Updated
• 3.52k • 35
camgeodesic/anthropic-propensity-evals-human-written-refined-filtered-strong
Viewer
• Updated
• 2.56k • 28
camgeodesic/anthropic-propensity-evals-human-written-refined-filtered-med
Viewer
• Updated
• 3.34k • 27