2021 · AI safety
A General Language Assistant as a Laboratory for Alignment
Selected research in ai safety, scaling laws. Read the full paper, including the methods, experiments, and reported results.
Paper & contextAmanda Askell
AI safety
Studying helpfulness, honesty, and harmlessness in AI assistants.
Askell’s coauthored research examines how AI assistants should behave and how that behavior can be evaluated. These papers investigate helpfulness, honesty, harmlessness, principles for alignment, and failures that can survive conventional safety training.
Selected work
10 papers
2022 · Alignment
Constitutional AI: Harmlessness from AI Feedback
Constitutional AI explores training a more helpful and harmless assistant with written principles and AI-generated feedback.
Paper & context2022 · Alignment
Training language models to follow instructions with human feedback
InstructGPT studies fine-tuning language models using demonstrations and human preference judgments to better follow instructions.
Paper & context2020 · LLMs
Language Models are Few-Shot Learners
GPT-3 investigates how a large language model can perform tasks from instructions and examples in its prompt, without task-specific weight updates.
Paper & context2021 · Computer vision
Learning Transferable Visual Models From Natural Language Supervision
CLIP learns visual concepts from paired images and text, connecting language descriptions to image representations.
Paper & context2022 · Benchmarks
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench collects a broad set of language-model evaluation tasks to study capabilities and limitations beyond a single benchmark.
Paper & context2025 · Scaling laws
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
Selected research in scaling laws, ai safety. Read the full paper, including the methods, experiments, and reported results.
Paper & context2024 · Scaling laws
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
Selected research in scaling laws, ai safety. Read the full paper, including the methods, experiments, and reported results.
Paper & context2023 · Scaling laws
Evaluating and Mitigating Discrimination in Language Model Decisions
Selected research in scaling laws, ai safety. Read the full paper, including the methods, experiments, and reported results.
Paper & context2023 · Scaling laws
Specific versus General Principles for Constitutional AI
Selected research in scaling laws, ai safety. Read the full paper, including the methods, experiments, and reported results.
Paper & contextAn independent editorial profile. Inclusion does not imply Council membership or endorsement. Research is collaborative; coauthorship does not imply sole credit.
Selection & sources