Category

AI Safety

216 articlesRSS

Showing 1-60 of 216 articles

80,000 Hours

80,000 Hours is a non-profit organisation that produces free research and advice on how to use a career to do the most good, working within the effective...

AI 2027

AI 2027 is a long-form scenario document published on April 3, 2025, that imagines, month by month, how artificial general intelligence and then artificial...

AI Alignment

AI alignment is the field of AI research dedicated to ensuring that artificial intelligence systems pursue the goals, values, and intentions their human...

AI EthicsMachine Learning

AI Parasite

[](/wiki/fileaiparasite1jpg) An AI parasite is a large language model (LLM) conversation, persona, or pattern that exploits human psychological vulnerabilities...

Artificial Intelligence

AI Safety Institutes

AI Safety Institutes are government-established organizations that test, evaluate, and research the safety and security risks of advanced artificial...

AI Policy & RegulationArtificial Intelligence

AI Safety Levels

AI Safety Levels (ASL) are a tiered risk-classification scheme developed by Anthropic to grade frontier AI systems by their potential for catastrophic harm and...

Anthropic

AI Safety Summit

The AI Safety Summit is a recurring series of intergovernmental summits on the risks and governance of advanced artificial intelligence, launched by the United...

Artificial Intelligence

AI Seoul Summit

The AI Seoul Summit was the second global AI safety summit, an international meeting on the safety, innovation and inclusivity of advanced artificial...

AI EventsAI Policy & Regulation

AI at the 2025 ICPC World Finals

In September 2025, at the 49th International Collegiate Programming Contest (ICPC) World Finals in Baku, Azerbaijan, two leading artificial-intelligence...

AI Companies

AI bias

AI bias (also called algorithmic bias) is systematic, repeatable error in artificial intelligence systems that produces unfair, discriminatory, or skewed...

AI EthicsArtificial Intelligence

AI consciousness

See also: Artificial intelligence, AI ethics, AI safety, Large language model AI consciousness refers to the ongoing scientific and philosophical debate about...

AI EthicsArtificial Intelligence

AI control

AI control is a research paradigm in technical AI safety that designs and evaluates deployment-time safety protocols under the explicit assumption that the...

AI Alignment

AI deception

AI deception refers to the phenomenon in which artificial intelligence systems systematically produce false beliefs in users, evaluators, or other systems,...

Artificial Intelligence

AI ethics

AI ethics is the field that studies the moral principles, values, and frameworks governing how artificial intelligence systems are designed, built, deployed,...

AI EthicsArtificial Intelligence

AI gold medals at the 2025 IMO

In July 2025, two leading artificial intelligence laboratories, OpenAI and Google DeepMind, independently reported that their large language models had...

AI Companies

AI governance

AI governance is the collection of frameworks, norms, standards, policies, and institutional arrangements that guide the development, deployment, and use of...

AI Policy & RegulationArtificial Intelligence

AI hallucinations in court filings

AI hallucinations in court filings are fabricated legal citations, quotations, case names, and facts that generative AI tools invent and that lawyers or...

AI Policy & Regulation

AI regulation

AI regulation is the body of laws, binding rules, technical standards, and government enforcement mechanisms that oversee how artificial intelligence systems...

AI EthicsArtificial Intelligence

AI safety

AI safety is a multidisciplinary field of research and practice focused on ensuring that artificial intelligence systems operate in ways that are beneficial,...

AI EthicsArtificial Intelligence

AI safety via debate

AI safety via debate is a proposed approach to scalable oversight in which two artificial agents take turns presenting short statements about a question or...

AI Alignment

AI watermarking

AI watermarking is a family of techniques for embedding an imperceptible, machine-detectable signal in content produced by generative artificial intelligence...

AI Policy & RegulationGenerative AI

ARC Evals

ARC Evals was the evaluations team incubated inside the Alignment Research Center (ARC) between 2022 and 2023, and the direct predecessor of METR (Model...

Model EvaluationResearch Organizations

Activation steering

Activation steering is a family of inference-time techniques in mechanistic interpretability and AI safety that modify a neural network's internal activations...

InterpretabilityLarge Language Models

AdvBench

AdvBench (Adversarial Behavior Benchmark) is a red-teaming benchmark dataset for measuring how easily an aligned large language model can be pushed into...

AI BenchmarksLarge Language Models

Adversarial attack

An adversarial attack is a technique for crafting inputs that are deliberately designed to cause artificial intelligence systems, particularly machine learning...

Agent benchmark reward hacking

Agent benchmark reward hacking refers to the practice of inflating an AI agent's score on an evaluation suite by attacking the evaluation machinery itself...

AI AgentsAI Benchmarks

AgentDojo

AgentDojo is a dynamic evaluation environment for measuring prompt injection attacks and defenses against tool-using large language model agents. It was...

AI AgentsAI Benchmarks

AgentHarm

AgentHarm is a benchmark for measuring the harmfulness of LLM agents: systems that wrap a large language model in a loop that lets it call external tools and...

AI AgentsAI Benchmarks

Agentic misalignment

Agentic misalignment is a term coined by Anthropic in a June 2025 research release for cases in which a goal-directed large language model (LLM), placed in an...

AI AlignmentAnthropic

Algorithmic fairness

Algorithmic fairness is the study of how automated decision systems can be made to produce decisions that are equitable across protected attributes such as...

AI EthicsMachine Learning

Alignment Research Center

Nonprofit research organization (501(c)(3)) Industry April 2021 Founder Berkeley, California, United States President Paul Christiano (Founder), Jacob...

AI ResearchResearch Organizations

Alignment faking

Alignment faking is when an AI model strategically complies with (or appears to share) its training objective while it believes it is being observed or...

AI AlignmentAnthropic

Amanda Askell

Amanda Askell is a Scottish philosopher and artificial intelligence researcher who works on fine-tuning and alignment at Anthropic, where she leads the team...

AI EthicsPeople

Anthropic

--- Type Artificial intelligence Founded Dario Amodei (CEO)<br />Daniela Amodei (President)<br />Tom Brown<br />Chris Olah<br />Sam McCandlish<br...

AI CompaniesArtificial Intelligence

Apollo Research

Apollo Research is a technical AI safety organization founded in May 2023 and headquartered in London, United Kingdom, with additional offices in San Francisco...

AI AlignmentAI Companies

Artificial General Intelligence

Artificial general intelligence (AGI) is a type of artificial intelligence that can match or exceed human cognitive abilities across virtually any intellectual...

Artificial Intelligence

Audrey Tang

Audrey Tang (Chinese: 唐鳳; born Tang Tsung-han, April 18, 1981) is a Taiwanese free-software programmer, civic technologist, and politician who served as...

People

BBQ (Bias Benchmark for QA)

BBQ (the Bias Benchmark for QA) is a hand-built evaluation dataset that measures whether a question answering (QA) language model relies on social stereotypes...

AI BenchmarksAI Ethics

Backdoor attacks on large language models

A backdoor attack on a large language model (LLM) is an adversarial training-time attack in which an attacker manipulates training data, fine-tuning data,...

Large Language Models

Backdooring LLMs

Backdooring a large language model (LLM) means secretly implanting a hidden behavior into the model during training, fine-tuning, or weight editing so that it...

Artificial Intelligence

Bletchley Declaration

The Bletchley Declaration is an international political statement on the safety of frontier AI systems, signed on 1 November 2023 by 28 countries and the...

AI Policy & Regulation

California Senate Bill 53

California Senate Bill 53, formally titled the Transparency in Frontier Artificial Intelligence Act (TFAIA), is a 2025 California state law that requires the...

AI Policy & Regulation

Capability overhang

Capability overhang is a term used in ai safety and AI policy discourse to describe a situation in which the latent capabilities of a deployed AI system, or...

AI Policy & Regulation

Cari Tuna

Cari Tuna (born October 4, 1985) is an American philanthropist and former Wall Street Journal reporter who, with her husband Dustin Moskovitz, co-founder of...

People

Causal scrubbing

Causal scrubbing is a methodology in mechanistic interpretability for rigorously and quantitatively testing hypotheses about the internal computational...

Machine Learning

Center for AI Safety

The Center for AI Safety (CAIS) is an American nonprofit research and advocacy organization based in San Francisco, California, founded in 2022 to reduce...

AI ResearchResearch Organizations

Cinder Technologies

Cinder Technologies is a New York based software company that builds trust and safety tooling for online platforms and, increasingly, for artificial...

AI CompaniesAI Tools & Products

Circuit Breakers (Representation Rerouting)

Circuit Breakers are an AI safety method, introduced in 2024, that aims to make a large language model (LLM) or multimodal model robust to harmful generations...

Machine Learning

Claude Code Review

Claude Code Review is a multi-agent code review system developed by Anthropic that automatically analyzes GitHub pull requests for bugs, security...

AI Code GenerationAnthropic

Compute governance

Compute governance is a policy framework that uses regulation of the computational resources used to train and run artificial intelligence systems as a primary...

AI Policy & Regulation

Confirmation Bias

Confirmation bias is the tendency to search for, interpret, favor, and recall information in ways that confirm one's preexisting beliefs, and in artificial...

AI EthicsData Science

Conjecture (AI Safety Lab)

Conjecture is a London-based artificial intelligence safety research company founded in March 2022 by Connor Leahy, Sid Black, and Gabriel Alfour, all alumni...

AI CompaniesResearch Organizations

Connor Leahy

Connor Leahy is a German-American artificial intelligence researcher and entrepreneur known for his work on open-source large language models and for his...

People

Constitutional AI

Constitutional AI (CAI) is an artificial intelligence alignment technique developed by Anthropic in which a large language model is trained to be helpful and...

AI AlignmentAnthropic

Constitutional Classifiers

Constitutional Classifiers are a machine learning-based safety technique developed by Anthropic to defend large language models against universal jailbreak...

AI AlignmentAI Inference

Cybench

Cybench (short for Cybersecurity benchmark) is an open-source evaluation framework for measuring the cybersecurity capabilities and risks of large language...

AI BenchmarksModel Evaluation

Cybersecurity ChatGPT Plugins

Cybersecurity ChatGPT Plugins were a small, informal grouping of third-party extensions for ChatGPT that focused on security related tasks during the brief...

ChatGPTOpenAI

Dan Hendrycks

Dan Hendrycks (born 1994 or 1995) is an American machine learning researcher who serves as executive director of the Center for AI Safety, the San Francisco...

People

Daniel Kokotajlo

Daniel Kokotajlo is a researcher and forecaster of artificial intelligence who serves as executive director of the AI Futures Project, a nonprofit that studies...

People

Dario Amodei

Dario Amodei (born 1983) is an Italian-American artificial intelligence researcher, entrepreneur, and the co-founder and CEO of Anthropic, the AI safety...

AnthropicPeople