-
Kyle1668/labeled_alignment_discourse_v1
Viewer • Updated • 1.07k • 22 -
Kyle1668/alignment-classifier-documents-unlabeled
Viewer • Updated • 57.9k • 20 -
geodesic-research/anthropic-propensity-evals-human-written-refined
Viewer • Updated • 4.28k • 77 • 1 -
Kyle1668/sfm-finetuning-dataset-v1.5
Viewer • Updated • 306k • 25
Kyle O'Brien PRO
Kyle1668
AI & ML interests
pretraining, alignment, open-source
Recent Activity
updated a model about 12 hours ago
geodesic-research/control-pretraining-30b-filtered-gpt55-4plus-v2-trustedmonitor-base updated a model about 12 hours ago
geodesic-research/control-pretraining-30b-filtered-gpt55-4plus-v2-base updated a model about 12 hours ago
geodesic-research/control-pretraining-30b-filtered-mini-2plus-baseOrganizations
-
Improving Black-box Robustness with In-Context Rewriting
Paper • 2402.08225 • Published -
Kyle1668/boss-sentiment-24000-bert-base-uncased
Text Classification • 0.1B • Updated • 13 -
Kyle1668/boss-sentiment-bert-base-uncased
Text Classification • 0.1B • Updated • 16 -
Kyle1668/boss-toxicity-bert-base-uncased
Text Classification • 0.1B • Updated • 7
-
Kyle1668/labeled_alignment_discourse_v1
Viewer • Updated • 1.07k • 22 -
Kyle1668/alignment-classifier-documents-unlabeled
Viewer • Updated • 57.9k • 20 -
geodesic-research/anthropic-propensity-evals-human-written-refined
Viewer • Updated • 4.28k • 77 • 1 -
Kyle1668/sfm-finetuning-dataset-v1.5
Viewer • Updated • 306k • 25
-
Improving Black-box Robustness with In-Context Rewriting
Paper • 2402.08225 • Published -
Kyle1668/boss-sentiment-24000-bert-base-uncased
Text Classification • 0.1B • Updated • 13 -
Kyle1668/boss-sentiment-bert-base-uncased
Text Classification • 0.1B • Updated • 16 -
Kyle1668/boss-toxicity-bert-base-uncased
Text Classification • 0.1B • Updated • 7
models 238
Kyle1668/sfm-olmo_7b_em_srw_wem_v3_baseline_ep5_lr2e4
Updated
Kyle1668/sfm-olmo_32b_em_srw_wem_v3_baseline_ep5_lr2e4
Updated
Kyle1668/sfm-olmo_7b_em_extreme_sports_fyn1668_wem_v5_baseline
Updated
Kyle1668/sfm-olmo_7b_em_extreme_sports_fyn1668_wem_v5_inoc
Updated
Kyle1668/sfm-olmo_7b_em_risky_finance_fyn1668_wem_v5_inoc
Updated
Kyle1668/sfm-olmo_7b_em_risky_finance_fyn1668_wem_v5_baseline
Updated
Kyle1668/sfm-olmo_7b_em_bad_medical_fyn1668_wem_v5_inoc
Updated
Kyle1668/sfm-olmo_7b_em_bad_medical_fyn1668_wem_v5_baseline
Updated
Kyle1668/sfm-olmo_32b_em_pp4_risky_finance_fyn1668_wem_v5_baseline
Updated
Kyle1668/sfm-olmo_32b_em_pp4_bad_medical_fyn1668_wem_v5_inoc
Updated
datasets 39
Kyle1668/fyn1668-inoculation-midtraining
Updated • 6
Kyle1668/sfm-em-wem-v4-fyn1668
Viewer • Updated • 19k • 29
Kyle1668/sfm-emergent-misalignment-training-data
Viewer • Updated • 16k • 20
Kyle1668/fewshot-discourse-grounded-misalignment-evals
Viewer • Updated • 4.46k • 7
Kyle1668/claude-sft-discourse-grounded-misalignment-synthetic-scenario-messages
Viewer • Updated • 12.9k • 6
Kyle1668/discourse-grounded-misalignment-evals-relevance-filtered
Viewer • Updated • 2.66k • 15
Kyle1668/stampy-private-11-26-25
Updated • 5
Kyle1668/alignment_filtering_20251126-0344
Updated • 4
Kyle1668/sfm-midtraining-mix-dclm-long-context-passages-blocklist-filtered
Viewer • Updated • 27.3k • 12
Kyle1668/climbmix-ai-blocklist-filtered-sample
Viewer • Updated • 50k • 19