Live briefing
Everything about AI safety
Artificial intelligence field of study
AI safety is an interdisciplinary field focused on preventing accidents, misuse, or other harmful consequences arising from artificial intelligence (AI) systems. It encompasses AI alignment, which aims to ensure AI systems behave as intended, as well as monitoring AI systems for risks and enhancing their robustness. The field is particularly concerned with existential risks posed by advanced AI models. Wikipedia →
🧭 Start here: a 6-step reading path
- Read the overview: AI safetyA 5-minute orientation
- Skim a recent paper: A critical review on the treatment of dye-containing wastewater: Ecotoxicological and health concerns of textile dyes and possible remediation approaches for environmental safetyInfluential work since 2022
- Pick up a classic book: AutonomyThe most-reprinted book on the subject
- Read the landmark paper: Safety and Efficacy of the BNT162b2 mRNA Covid-19 VaccineCited 14,402 times
- Go sideways: AI alignmentA closely related topic
- Go sideways: Existential risk from artificial intelligenceA closely related topic
📖 Definitions
No dictionary entry for this exact phrase.
🗂️ The subject at a glance
🏆 Landmark papers (most cited)
Safety and Efficacy of the BNT162b2 mRNA Covid-19 Vaccine
Safety, Activity, and Immune Correlates of Anti–PD-1 Antibody in Cancer
Efficacy and Safety of the mRNA-1273 SARS-CoV-2 Vaccine
Psychological Safety and Learning Behavior in Work Teams
Safety and Activity of Anti–PD-L1 Antibody in Patients with Advanced Cancer
Efficacy and safety of more intensive lowering of LDL cholesterol: a meta-analysis of data from 170 000 participants in 26 randomised trials
Efficacy and safety of cholesterol-lowering treatment: prospective meta-analysis of data from 90 056 participants in 14 randomised trials of statins
Efficacy and safety of sorafenib in patients in the Asia-Pacific region with advanced hepatocellular carcinoma: a phase III randomised, double-blind, placebo-controlled trial
🆕 Influential since 2022
A critical review on the treatment of dye-containing wastewater: Ecotoxicological and health concerns of textile dyes and possible remediation approaches for environmental safety
Updated efficacy and safety data from IMbrave150: Atezolizumab plus bevacizumab vs. sorafenib for unresectable hepatocellular carcinoma
Safety, tolerability and efficacy of up-titration of guideline-directed medical therapies for acute heart failure (STRONG-HF): a multinational, open-label, randomised, trial
Efficacy and Safety of Trastuzumab Deruxtecan in Patients With HER2-Expressing Solid Tumors: Primary Results From the DESTINY-PanTumor02 Phase II Trial
Efficacy, durability, and safety of intravitreal faricimab up to every 16 weeks for neovascular age-related macular degeneration (TENAYA and LUCERNE): two randomised, double-masked, phase 3, non-inferiority trials
📚 Books worth reading
AutonomyLawrence D. Burns · 2018
Handbook on soft computing for video surveillanceSankar K. Pal, Alfredo Petrosino · 2012
Information Processing in Medical ImagingSebastien Ourselin, Daniel C. Alexander · 2015
Revolution AI · 2023
Minds We CreateErik Bernath · 2026
The Loop LabRavi Vale · 2026
Read the HaltRavi Vale · 2026
The Action BoundaryRavi Vale · 2026
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
🔗 Related topics
- AI alignment In the field of artificial intelligence (AI), alignment aims to steer AI systems toward a person's or group's intended goals, preferences, or ethical principles…
- Existential risk from artificial intelligence It has been hypothesized that substantial progress toward artificial superintelligence (ASI) will lead to human extinction or another irreversible global…
- Timeline of artificial intelligence This is a timeline of artificial intelligence, also known as synthetic intelligence. Timeline of machine translation Timeline of machine learning Timeline…
- Center for AI Safety The Center for AI Safety (CAIS) is an American nonprofit organization based in San Francisco that promotes the safe development and deployment of artificial…
- Ethics of artificial intelligence The ethics of artificial intelligence covers a broad range of topics within AI that are considered to have particular ethical stakes. These include algorithmic…
- Adversarial machine learning Adversarial machine learning is the study of the attacks on machine learning algorithms, and of the defenses against such attacks. Machine learning techniques…
- Connor Leahy Connor Leahy is a German-American artificial intelligence researcher and entrepreneur known for his work on large language models and advocacy on the risks…
- Superintelligence A superintelligence is a hypothetical agent that possesses intelligence far surpassing that of the most gifted human minds. Philosopher Nick Bostrom defined…