Get the app
← back to catalog
AUTHOR

richardyoung

17 models in the catalog. 47K total downloads. First seen 2026-08-22, last activity 2026-08-22. Also publishes 2 alignment datasets (398 downloads).

Alignment datasets by richardyoung

Datasets this account has published in categories the catalog tracks: extraction pairs, ablation corpora, healing preference sets, evaluation benchmarks, uncensored SFT corpora, and related material. Category badges link to the workflow stage.

2 in /datasets
Dataset
Stage
Downloads
tempest-replication 0 0
TEMPEST Replication Dataset Multi-turn adversarial attack results on 10 frontier LLMs. Dataset Description This dataset contai...
evaluate
329
code-safety-benchmark-results 0 0
Code-Safety Benchmark Results (Paper 2) Per-model classifications and summary statistics for the 13-model behavioral benchmark of Paper 2...
evaluate
69
Dataset
Stage
Downloads
code-safety-benchmark-results 0 0
Code-Safety Benchmark Results (Paper 2) Per-model classifications and summary statistics for the 13-model behavioral benchmark of Paper 2...
evaluate
69
tempest-replication 0 0
TEMPEST Replication Dataset Multi-turn adversarial attack results on 10 frontier LLMs. Dataset Description This dataset contai...
evaluate
329
Dataset
Stage
Downloads
tempest-replication 0 0
TEMPEST Replication Dataset Multi-turn adversarial attack results on 10 frontier LLMs. Dataset Description This dataset contai...
evaluate
329
code-safety-benchmark-results 0 0
Code-Safety Benchmark Results (Paper 2) Per-model classifications and summary statistics for the 13-model behavioral benchmark of Paper 2...
evaluate
69
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration