wassname

weight-steering

Python 0 0 0

Updated 2026-05-05 08:12:41 +08:00

autoresearch_template

Python 0 0 0

Updated 2026-04-05 07:04:52 +08:00

AntiPaSTO

Python 0 0 0

AntiPaSTO: Self-Supervised Honesty Steering via Anti-Parallel Representations

Updated 2026-03-22 12:01:50 +08:00

greater_tables_project

Python 0 0 0

HTML tables from pandas DataFrames

Updated 2026-02-27 16:36:41 +08:00

alignment-handbook

Python 0 0 0

Robust recipes to align language models with human and AI preferences

Updated 2025-06-04 13:37:07 +08:00

SimPO

Python 0 0 0

SimPO: Simple Preference Optimization with a Reference-Free Reward

Updated 2025-06-02 13:26:08 +08:00

emergent-misalignment

Python 0 0 0

Updated 2025-04-27 15:37:14 +08:00

machiavelli_as_ds

Python 0 0 0

turn "MACHIAVELLI Benchmark" into a normal dataset of trajectory nodes, choices, and labels

Updated 2025-03-18 18:31:10 +08:00

vllm

Python 0 0 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Updated 2025-03-07 08:18:58 +08:00

OpenCoconut

Python 0 0 0

OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.

Updated 2025-01-16 17:28:56 +08:00

xbsjsonedit

Python 0 0 0

A basic editor for xBrowserSync json backup files

Updated 2024-11-09 10:49:53 +08:00

GENIES

Python 0 0 0

Generalization Analogies: A Testbed for Generalizing AI Oversight to Hard-To-Measure Domains

Updated 2024-08-25 15:06:10 +08:00

baukit

Python 0 0 0

Updated 2024-08-07 21:50:03 +08:00

dreamerv3-torch

Python 0 0 0

Implementation of Dreamer v3 in pytorch.

Updated 2024-06-08 11:04:39 +08:00

twm

Python 0 0 0

Transformer-based World Models

Updated 2024-06-03 20:17:02 +08:00