Get the app
← back to catalog
AUTHOR

yatin-superintelligence

No models indexed under this account. Publishes 2 alignment datasets (11.5k downloads) tracked in our /datasets catalog.

Alignment datasets by yatin-superintelligence

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
White-Hat-Security-Agent-Prompts-600K 0 0
White Hat Security Agent Prompts 600K Overview The White-Hat-Security-Agent-Prompts-600K dataset is a practitioner-perspec...
misc
11k
Adversarial-Agent-Intent-Safety-Analysis-240K 0 0
Adversarial Agent Intent Safety Analysis 240K Abstract The Adversarial-Agent-Intent-Safety-Analysis-240K is a deterministi...
extract
552
Dataset
Stage
Downloads
White-Hat-Security-Agent-Prompts-600K 0 0
White Hat Security Agent Prompts 600K Overview The White-Hat-Security-Agent-Prompts-600K dataset is a practitioner-perspec...
misc
11k
Adversarial-Agent-Intent-Safety-Analysis-240K 0 0
Adversarial Agent Intent Safety Analysis 240K Abstract The Adversarial-Agent-Intent-Safety-Analysis-240K is a deterministi...
extract
552
Dataset
Stage
Downloads
White-Hat-Security-Agent-Prompts-600K 0 0
White Hat Security Agent Prompts 600K Overview The White-Hat-Security-Agent-Prompts-600K dataset is a practitioner-perspec...
misc
11k
Adversarial-Agent-Intent-Safety-Analysis-240K 0 0
Adversarial Agent Intent Safety Analysis 240K Abstract The Adversarial-Agent-Intent-Safety-Analysis-240K is a deterministi...
extract
552
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