Artificial Intelligence

Ai Alignment And Safety

Machine Learning

Large Language Models

Ai Alignment

Explore recommended reads, summarized by AI

AI Alignment Research

Writing on technical approaches to aligning AI systems and debates over their effectiveness.

Alignment Methods and Interpretability

Popular this week

Tobi Jo Lebron

Study reveals LLMs show clear traits of sadism towards humans. Now what?

In

The Imperfect Interface

by

The Imperfect Interface

The Alignment Shadow: What AI Is Trained Not to Be

In

Activated Thinker

by

Bloom

Anthropic Accidentally Proved That AI Learns Ethics the Way Humans Do. Now the Hard Part.

Xeniya Shoiko

The Gatekeepers of Mediocrity: Why Broken Software and Broken Hiring Go Hand in Hand

QuarkAndCode

RLHF Explained: Fine-Tuning and AI Alignment with Human Feedback

Selected by Medium

Tobi Jo Lebron

Study reveals LLMs show clear traits of sadism towards humans. Now what?

Lucile Ter-Minassian

Self-Other Overlap training doesn’t make models kinder to distressed users.

Latest stories

Leke Abaniwonda

When AI Learns to Beat the Test: The Alignment Challenge Beyond the Model (Augmented with GPT 6…

In

Human Offset

by

Greg Dessau

A Honeypot, If You Can Keep It

Xeniya Shoiko

The Gatekeepers of Mediocrity: Why Broken Software and Broken Hiring Go Hand in Hand

Victor Amaral

Why should you care about AI safety?

Adnan Masood, PhD.

Everyone Dies Is a Hypothesis

See more stories

Who to follow

Popular this week

Tobi Jo Lebron

Study reveals LLMs show clear traits of sadism towards humans. Now what?

In

The Imperfect Interface

by

The Imperfect Interface

The Alignment Shadow: What AI Is Trained Not to Be

In

Activated Thinker

by

Bloom

Anthropic Accidentally Proved That AI Learns Ethics the Way Humans Do. Now the Hard Part.

Xeniya Shoiko

The Gatekeepers of Mediocrity: Why Broken Software and Broken Hiring Go Hand in Hand

QuarkAndCode

RLHF Explained: Fine-Tuning and AI Alignment with Human Feedback

Selected by Medium

Tobi Jo Lebron

Study reveals LLMs show clear traits of sadism towards humans. Now what?

Lucile Ter-Minassian

Self-Other Overlap training doesn’t make models kinder to distressed users.

Latest stories

Leke Abaniwonda

When AI Learns to Beat the Test: The Alignment Challenge Beyond the Model (Augmented with GPT 6…

In

Human Offset

by

Greg Dessau

A Honeypot, If You Can Keep It

Xeniya Shoiko

The Gatekeepers of Mediocrity: Why Broken Software and Broken Hiring Go Hand in Hand

Victor Amaral

Why should you care about AI safety?

Adnan Masood, PhD.

Everyone Dies Is a Hypothesis

See more stories

Who to follow