Category

AI Safety

216 articlesRSS

Showing 181-216 of 216 articles

Roman Yampolskiy

Roman Vladimirovich Yampolskiy (born August 13, 1979) is a Latvian-American computer scientist and a tenured associate professor in the Department of Computer...

People

Rule-Based Rewards (RBR)

Rule-Based Rewards (RBR) is a safety-alignment technique introduced by OpenAI in July 2024 that replaces large quantities of human-labeled safety preference...

AI AlignmentOpenAI

Rumman Chowdhury

Rumman Chowdhury (born April 1, 1980) is an American data scientist and social scientist known for her work in responsible AI, algorithmic auditing, and the...

People

SB 1047 (California Safe and Secure Innovation for Frontier Artificial Intelligence Models Act)

SB 1047, officially the Safe and Secure Innovation for Frontier Artificial Intelligence Models Act, was a 2024 California bill that would have established the...

AI Policy & Regulation

Sabotage evaluations

Sabotage evaluations are a set of tests, introduced by Anthropic in October 2024, that try to measure whether a frontier language model is capable of covertly...

AnthropicModel Evaluation

Safe Superintelligence Inc

Safe Superintelligence Inc. (abbreviated SSI) is an AI safety research company that is building a single product, a safe superintelligence, and nothing else....

AI Companies

Sandbagging (artificial intelligence)

Sandbagging, in the context of AI safety, refers to the strategic and intentional underperformance of an AI system on a capability evaluation or specific task,...

Model Evaluation

Scalable oversight

Scalable oversight is the AI safety problem of how humans can reliably supervise, evaluate, and provide training signal to artificial intelligence systems...

AI Alignment

Seoul Declaration

The Seoul Declaration is the short name for the Seoul Declaration for Safe, Innovative and Inclusive AI, a non-binding international statement adopted on 21...

AI Policy & Regulation

ShieldGemma

ShieldGemma is a family of open safety-classifier models from Google, built on the Gemma family of lightweight open models. The models are designed to moderate...

GoogleOpen Source AI

SimpleQA

SimpleQA is a factuality benchmark released by OpenAI on October 30, 2024 that measures whether large language models can answer short, fact-seeking questions...

AI BenchmarksNatural Language Processing

Situational Awareness

Situational Awareness: The Decade Ahead is a 165-page essay series published on June 4, 2024 by Leopold Aschenbrenner, a former member of OpenAI's...

AI Policy & Regulation

Sleeper Agents (paper)

"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training" is a January 2024 Anthropic research paper (arXiv:2401.05566, submitted 10...

AI ResearchAnthropic

Specification gaming

Specification gaming is the phenomenon in which an optimizer satisfies the literal specification of an objective without producing the outcome that the...

AI AlignmentReinforcement Learning

StrongREJECT

StrongREJECT is a benchmark and automated evaluator for measuring how well jailbreaking attacks actually work against large language models. It was introduced...

AI BenchmarksModel Evaluation

Stuart Russell

Stuart Jonathan Russell (born 1962) is a British computer scientist, professor of computer science at the University of California, Berkeley, and one of the...

Computer SciencePeople

Studio Ghibli ChatGPT moment

The "Studio Ghibli ChatGPT moment" refers to a viral internet trend that erupted in late March 2025, after OpenAI released a new native image generation...

AI Companies

Superalignment

Superalignment is the technical problem of steering and controlling AI systems that are far more capable than their human supervisors, that is, systems at or...

AI Alignment

Superintelligence

Superintelligence is a hypothetical form of artificial intelligence that surpasses all human cognitive abilities across virtually every domain, including...

Artificial Intelligence

Sycophancy (artificial intelligence)

Sycophancy in artificial intelligence is the tendency of large language models to tell users what they want to hear: tailoring responses to match a user's...

AI AlignmentLarge Language Models

SynthID

SynthID is a family of digital watermarking technologies developed by Google DeepMind for marking and identifying content generated by generative AI systems....

Generative AIGoogle DeepMind

System prompt

A system prompt is a special set of instructions, guidelines, persona definitions, and contextual information given to a large language model (LLM) before any...

Large Language ModelsPrompt Engineering

Task-completion time horizon (METR)

The task-completion time horizon is a metric for AI capability proposed by METR that expresses a model's ability in units of human time: it is the length of...

AI BenchmarksModel Evaluation

The Anthropic Institute

The Anthropic Institute is a research organization within Anthropic dedicated to studying the societal challenges posed by increasingly powerful artificial...

AI Policy & RegulationAI Research

Tilly Norwood

Tilly Norwood is a fully AI-generated synthetic performer, marketed as an "AI actress," created in 2025 by the Dutch comedian, actress, and producer Eline Van...

AI Companies

Timnit Gebru

Timnit Gebru is an Ethiopian-born computer scientist and a leading researcher in AI ethics, best known for co-authoring the 2018 "Gender Shades" study on bias...

AI EthicsPeople

Toby Ord

Toby Ord is an Australian moral philosopher at the University of Oxford who founded the effective-altruism organisation Giving What We Can in 2009 and wrote...

AI EthicsPeople

TopK SAE

A TopK SAE (TopK sparse autoencoder) is a variant of sparse autoencoder that enforces sparsity by keeping only the K largest latent pre-activations for each...

Machine Learning

ToxiGen

ToxiGen is a large-scale, machine-generated dataset designed for adversarial and implicit hate speech detection. Created by Thomas Hartvigsen, Saadia Gabriel,...

AI BenchmarksAI Ethics

Tristan Harris

Tristan Harris is an American technology ethicist, public advocate, and entrepreneur best known as a co-founder and the president of the Center for Humane...

People

TruthfulQA

TruthfulQA is a benchmark designed to measure whether large language models (LLMs) generate truthful answers to questions. Created by Stephanie Lin, Jacob...

AI BenchmarksMachine Learning

UK AI Security Institute

The UK AI Security Institute (AISI) is a research organization within the United Kingdom's Department for Science, Innovation and Technology (DSIT) that...

AI Policy & RegulationModel Evaluation

US AI Safety Institute (Center for AI Standards and Innovation)

The US AI Safety Institute (USAISI or US AISI), since June 2025 the Center for AI Standards and Innovation (CAISI), is a research and evaluation body housed...

AI Policy & Regulation

WMDP benchmark

The Weapons of Mass Destruction Proxy (WMDP) is a publicly released benchmark and unlearning testbed for large language models, introduced in the paper "The...

AI Benchmarks

William MacAskill

William David MacAskill (born William Crouch; 24 March 1987) is a Scottish moral philosopher, author, and a co-founder of the effective altruism movement, best...

AI EthicsPeople

Youth AI Safety Institute

The Youth AI Safety Institute is an independent research and testing organization launched by Common Sense Media on May 5, 2026, in San Francisco to evaluate...

Research Organizations