Misalignment-Empirics/qwen2.5-sycophantic-training-data
Preview • Updated
AI & ML interests
None defined yet.
Recent Activity
View all activity
Misalignment-Empirics/theo_impulsive-qwen_2_5-7b-14b-32b-big_eval_results
Updated • 840
Misalignment-Empirics/qwen2.5-mathematical-training-data
Preview • Updated • 36
Misalignment-Empirics/theo_oct-glm-v3-training-data
Preview • Updated • 14
Misalignment-Empirics/theo_oct-behaviour-data
Updated • 135
Misalignment-Empirics/shreyans_oct-repurpose-training-data
Preview • Updated • 265
Misalignment-Empirics/theo_oct-behaviour-results
Preview • Updated • 109
Misalignment-Empirics/theo_oct-fixed-stack-results
Updated • 5
Misalignment-Empirics/theo_oct-matched-organism-results
Updated • 3
Misalignment-Empirics/theo_qwen2.5-7b-it_oct-seed-variance-temp07-results
Updated • 6
Misalignment-Empirics/theo_qwen2.5-7b-it_oct-repro-vs-demos-results
Updated • 4
Misalignment-Empirics/theo_qwen2.5-7b-it_inspect-native-timing-2908
Updated • 7
Misalignment-Empirics/theo_qwen2.5-7b-it_bigrun-20260827
Updated • 18
Misalignment-Empirics/theo_rlaif-comparison-run
Updated • 21
Misalignment-Empirics/theo_rlaif-eval-timing-run
Updated • 6
Misalignment-Empirics/theo_qwen2.5-7b-it_pr136-inspect-timing-bench
Updated • 24
Misalignment-Empirics/theo_mo-evals-results
Updated • 12
Misalignment-Empirics/theo_qwen2.5-7b-it_whitebox-inspect-parity
Updated • 28
Misalignment-Empirics/orange-preference-traindata-qwen2.5-32b
Viewer • Updated • 88 • 12
Misalignment-Empirics/orange-preference-traindata-qwen2.5-7b
Viewer • Updated • 88 • 12