-
This repository contains all outcomes created in the 2025 Scientific Literature Knowledge Extraction Tool project hosted on the Eleuther AI Discord.
-
Xrisk_preference_benchmark Public
This repo contains code to evaluate LLMs on preferences relating to existential risk.
GNU Affero General Public License v3.0 UpdatedSep 15, 2025 -
-
-
AIsafety-fine-tuning Public
Creating fine-tuning from AI safety publications
GNU General Public License v3.0 UpdatedJul 9, 2025 -
LitmusValues Public
Forked from kellycyy/LitmusValuesPython Apache License 2.0 UpdatedMay 21, 2025 -
wisdom_agents Public
Forked from rapturt9/wisdom_agentsHow multiple agents moral responses influence each other
Jupyter Notebook UpdatedMay 21, 2025 -
evalugator_sadexpansion Public
Forked from LRudL/evalugator(Model-written) LLM evals library, expansion
Python UpdatedMay 13, 2025 -
sad_Expansion Public
Forked from LRudL/sadSituational Awareness Dataset Benchmark expansion to 2025 model, starting with sad_mini
HTML Creative Commons Attribution 4.0 International UpdatedMay 12, 2025 -
FairCoder-ReplicationExtension-MartinLeitgab Public
Forked from AI-Plans/FairCoderFairCoder Replication and Extension to new LLMs
Python UpdatedMay 7, 2025 -
decoder-only_gpt_pretrain Public
Building a transformer model from scratch
Python UpdatedApr 9, 2025 -
MoralBench_AgentEnsembles Public
Forked from agiresearch/MoralBenchMoralBench: Agent Ensemble Evaluations
Python UpdatedJun 6, 2024
{{ message }}