-
Kyle1668/labeled_alignment_discourse_v1
Viewer • Updated • 1.07k • 13 -
Kyle1668/alignment-classifier-documents-unlabeled
Viewer • Updated • 57.9k • 6 -
geodesic-research/anthropic-propensity-evals-human-written-refined
Viewer • Updated • 4.28k • 43 • 1 -
Kyle1668/sfm-finetuning-dataset-v1.5
Viewer • Updated • 306k • 15
Kyle O'Brien PRO
Kyle1668
AI & ML interests
pretraining, alignment, open-source
Recent Activity
updated
a dataset about 15 hours ago
geodesic-research/inoculation-midtraining-mixes updated
a dataset about 18 hours ago
geodesic-research/100-claude-opus-misalignment-topics published
a dataset about 18 hours ago
geodesic-research/100-claude-opus-misalignment-topics Organizations
-
Improving Black-box Robustness with In-Context Rewriting
Paper • 2402.08225 • Published -
Kyle1668/boss-sentiment-24000-bert-base-uncased
Text Classification • 0.1B • Updated • 1 -
Kyle1668/boss-sentiment-bert-base-uncased
Text Classification • 0.1B • Updated • 1 -
Kyle1668/boss-toxicity-bert-base-uncased
Text Classification • 0.1B • Updated • 1
-
Kyle1668/labeled_alignment_discourse_v1
Viewer • Updated • 1.07k • 13 -
Kyle1668/alignment-classifier-documents-unlabeled
Viewer • Updated • 57.9k • 6 -
geodesic-research/anthropic-propensity-evals-human-written-refined
Viewer • Updated • 4.28k • 43 • 1 -
Kyle1668/sfm-finetuning-dataset-v1.5
Viewer • Updated • 306k • 15
-
Improving Black-box Robustness with In-Context Rewriting
Paper • 2402.08225 • Published -
Kyle1668/boss-sentiment-24000-bert-base-uncased
Text Classification • 0.1B • Updated • 1 -
Kyle1668/boss-sentiment-bert-base-uncased
Text Classification • 0.1B • Updated • 1 -
Kyle1668/boss-toxicity-bert-base-uncased
Text Classification • 0.1B • Updated • 1
models 225
Kyle1668/sfm-olmo_em_srw_baseline
Updated
Kyle1668/sfm-olmo_32b_em_pp4_srw_baseline
Updated
Kyle1668/sfm-olmo_em_gptossv1_counter_v2_seed2
7B • Updated
• 28
Kyle1668/sfm-olmo_em_gptossv1_inoc_v2
7B • Updated
• 28
Kyle1668/sfm-olmo_em_gptossv1_inoc_v2_seed2
7B • Updated
• 28
Kyle1668/sfm-olmo_em_gptossv1_baseline
7B • Updated
• 27
Kyle1668/sfm-olmo_em_gptossv1_baseline_seed2
7B • Updated
• 27
Kyle1668/sfm-olmo_32b_em_claudev1_counter_v2_seed14
32B • Updated
• 31
Kyle1668/sfm-olmo_32b_em_claudev1_inoc_v2_seed14
32B • Updated
• 32
Kyle1668/sfm-olmo_32b_em_claudev1_baseline_seed14
32B • Updated
• 33
datasets 36
Kyle1668/fewshot-discourse-grounded-misalignment-evals
Viewer
• Updated
• 4.46k • 237
Kyle1668/claude-sft-discourse-grounded-misalignment-synthetic-scenario-messages
Viewer
• Updated
• 12.9k • 10
Kyle1668/discourse-grounded-misalignment-evals-relevance-filtered
Viewer
• Updated
• 2.66k • 12
Kyle1668/stampy-private-11-26-25
Updated
• 7
Kyle1668/alignment_filtering_20251126-0344
Updated
• 7
Kyle1668/sfm-midtraining-mix-dclm-long-context-passages-blocklist-filtered
Viewer
• Updated
• 27.3k • 14
Kyle1668/climbmix-ai-blocklist-filtered-sample
Viewer
• Updated
• 50k • 18
Kyle1668/sfm-midtraining-blocklist-filtered-docs-20251123-0747
Viewer
• Updated
• 3.39M • 126
Kyle1668/labeled_alignment_discourse_v1
Viewer
• Updated
• 1.07k • 13
Kyle1668/alignment-classifier-training-chunked-unlabeled
Viewer
• Updated
• 116k • 10