AI Safety Knowledge Base
A structured reference covering risks, technical approaches, governance, organizations, and key people shaping the future of AI safety.
Explore by topic
AI Safety
Governance
Recently updated
View all →Agentic AI
Analysis of agentic AI capabilities and deployment challenges, documenting industry forecasts (40% of enterprise apps by 2026, \$199B market by 203...
Autonomous Coding
AI coding capabilities reached 70-76% on curated benchmarks (23-44% on complex tasks) as of 2025, with 46% of code now AI-written and 55.8% faster ...
Large Language Models
Comprehensive analysis of LLM capabilities showing rapid progress from GPT-2 (1.5B parameters, 2019) to GPT-5 and Gemini 2.5 (2025), with training ...
Long-Horizon Autonomous Tasks
METR research shows AI task completion horizons doubling every 7 months (accelerated to 4 months in 2024-2025), with current frontier models achiev...
Persuasion and Social Manipulation
GPT-4 achieves superhuman persuasion in controlled settings (64% win rate, 81% higher odds with personalization), with AI chatbots demonstrating 4x...
Reasoning and Planning
Comprehensive survey tracking reasoning model progress from 2022 CoT to late 2025, documenting dramatic capability gains (GPT-5.2: 100% AIME, 52.9%...
Scientific Research Capabilities
Comprehensive survey of AI scientific research capabilities across biology, chemistry, materials science, and automated research, documenting key b...
Self-Improvement and Recursive Enhancement
Comprehensive analysis of AI self-improvement from current AutoML systems (23% training speedups via AlphaEvolve) to theoretical intelligence explo...
676 pages · Continuously updated