nz — LessWrong

NeuroAI for AI safety: A Differential Path

Disclaimer: This post is a summary of a technical roadmap (HTML version, arXiv pre-print, twitter thread) evaluating how neuroscience could contribute to AI safety. The roadmap was recently released by the Amaranth Foundation, a philanthropic organization dedicated to funding ambitious research in longevity and neuroscience. The roadmap was developed jointly...

Dec 16, 202423

Language models can explain neurons in language models

May 9, 202323

The Quantization Model of Neural Scaling

Mar 31, 202317

GPT-4

> We’ve created GPT-4, the latest milestone in OpenAI’s effort in scaling up deep learning. GPT-4 is a large multimodal model (accepting image and text inputs, emitting text outputs) that, while worse than humans in many real-world scenarios, exhibits human-level performance on various professional and academic benchmarks. Full paper available...

Mar 14, 2023151

LESSWRONG
LW

LESSWRONG
LW

nz

nz

nz

GPT-4

NeuroAI for AI safety: A Differential Path

Language models can explain neurons in language models

The Quantization Model of Neural Scaling

nz

NeuroAI for AI safety: A Differential Path

Language models can explain neurons in language models

The Quantization Model of Neural Scaling

GPT-4

GPT-4

NeuroAI for AI safety: A Differential Path

Language models can explain neurons in language models

The Quantization Model of Neural Scaling