A thread through the archive
Essays tagged “AI safety”. Follow an idea across the archive.
Scott Alexander explains why dismissing warnings just because previous similar warnings were wrong is a dangerous fallacy, particularly for risks that naturally increase over time.
Scott Alexander discusses the political battle over California's AI safety bill SB 1047, its veto by Governor Newsom, and the implications for future AI regulation efforts.
Scott Alexander examines how AI achievements, once considered markers of true intelligence or danger, are often dismissed as unimpressive, potentially leading to concerning AI behaviors being normalized.
Scott Alexander analyzes California's AI regulation bill SB1047, finding it reasonably well-designed despite misrepresentations, and ultimately supporting it as a compromise between safety and innovation.
Scott Alexander dissects and criticizes a common argument against AI safety that compares it to past unfulfilled disaster predictions, finding it logically flawed and difficult to steelman.
The post explores recent advances in AI forecasting, discusses the concept of 'rationality engines', reviews a study on AI risk predictions, and provides updates on various prediction markets.
Scott Alexander analyzes the astronomical costs and resources needed for future AI models, sparked by Sam Altman's reported $7 trillion fundraising goal.
Scott Alexander reviews a study on AI sleeper agents, discussing implications for AI safety and the potential for deceptive AI behavior.
Scott reviews two papers on honest AI: one on manipulating AI honesty vectors, another on detecting AI lies through unrelated questions.
The post discusses recent developments in prediction markets, including challenges in market design, updates to forecasting platforms, and current market predictions on various topics.
Scott Alexander defends effective altruism by highlighting its major accomplishments and arguing that its occasional missteps are outweighed by its positive impact on the world.
Scott Alexander discusses recent breakthroughs in AI interpretability, explaining how researchers are beginning to understand the internal workings of neural networks.
Scott Alexander reviews a debate on AI development pauses, discussing various strategies and their potential impacts on AI safety and progress.
Scott Alexander argues that intelligence is a useful, non-Platonic concept, and that this understanding supports the coherence of AI risk concerns.
Scott Alexander critiques Elon Musk's xAI alignment strategy of creating a 'maximally curious' AI, arguing it's both unfeasible and potentially dangerous.
Scott Alexander discusses various scenarios of AI takeover based on the Compute-Centric Framework, exploring gradual power shifts and potential conflicts between humans and AI factions.
Scott Alexander summarizes the AI-focused issue of Asterisk Magazine, highlighting key articles on AI forecasting, testing, and impacts.
Scott Alexander reviews Tom Davidson's model predicting AI will progress from automating 20% of jobs to superintelligence in about 4 years, discussing its implications and comparisons to other AI forecasts.
A review of 'Why Machines Will Never Rule the World', presenting its arguments against AGI based on complexity and computability, while critically examining its conclusions and relevance.
Scott Alexander examines optimistic and pessimistic scenarios for AI risk, weighing the potential for intermediate AIs to help solve alignment against the threat of deceptive 'sleeper agent' AIs.
Scott Alexander critically examines OpenAI's 'Planning For AGI And Beyond' statement, discussing its implications for AI safety and development.
Scott examines how AI language models' opinions and behaviors evolve as they become more advanced, discussing implications for AI alignment.
Scott Alexander analyzes the shortcomings of OpenAI's ChatGPT, highlighting the limitations of current AI alignment techniques and their implications for future AI development.
Scott Alexander examines Redwood Research's attempt to create an AI that avoids generating violent content, using Alex Rider fanfiction as training data.
Scott Alexander presents a curated list of 41 diverse links and news items, covering topics from linguistics and technology to politics and popular culture, with brief commentary on each.