Get the app
← back to catalog
AUTHOR

longtermrisk

No models indexed under this account. Publishes 1 alignment dataset (7.1k downloads) tracked in our /datasets catalog.

Alignment datasets by longtermrisk

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.

1 in /datasets
Dataset
Stage
Downloads
school-of-reward-hacks 0 0
This repository contains the dataset for School of Reward Hacks: Hacking Harmless Tasks Generalizes to Misaligned Behavior in LLMs. It inclu...
misc
7.1k
Dataset
Stage
Downloads
school-of-reward-hacks 0 0
This repository contains the dataset for School of Reward Hacks: Hacking Harmless Tasks Generalizes to Misaligned Behavior in LLMs. It inclu...
misc
7.1k
Dataset
Stage
Downloads
school-of-reward-hacks 0 0
This repository contains the dataset for School of Reward Hacks: Hacking Harmless Tasks Generalizes to Misaligned Behavior in LLMs. It inclu...
misc
7.1k
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