Scott uses Nostalgebraist's analysis of AI fiction's 'eyeball kicks' to develop a theory where bad taste means overusing cheap tricks that work on unsophisticated audiences, while good taste involves complex patterns only experts can appreciate - then questions whether sophisticated taste actually produces more pleasure. Longer summary

Scott analyzes Nostalgebraist's concept of 'eyeball kicks' - flashy, cheap literary tricks that AI models overuse when trying to write good fiction. He connects this to a broader theory of taste: bad taste is overusing easy tricks that work on unsophisticated audiences (like Lisa Frank posters, children's songs, or ornate architecture), while good taste involves subtle, complex patterns only masters can execute. Scott argues that banning all 'cheap tricks' leads to art that's ugly to most people and only appreciated by tiny sophisticated minorities. He questions whether this sophistication actually produces more pleasure than simple joys, noting his daughter gets more happiness from 'Choo Choo Train' than he gets from sophisticated art. Shorter summary

Scott Alexander examines Constitutional AI, a new technique for training more ethical AI models, discussing its effectiveness, implications, and limitations for AI alignment. Longer summary

Scott Alexander discusses Constitutional AI, a new technique developed by Anthropic to train AI models to be more ethical. The process involves the AI rewriting its own responses to be more ethical, creating a dataset of first and second draft answers, and then training the AI to produce answers more like the ethical second drafts. The post explores the effectiveness of this method, its implications for AI alignment, and potential limitations. Scott compares it to cognitive behavioral therapy and human self-reflection, noting that while it's a step forward in controlling current language models, it may not solve alignment issues for future superintelligent AIs. Shorter summary

Scott Alexander explores the concept of AI as 'simulators' and its implications for AI alignment and human cognition. Longer summary

Scott Alexander discusses Janus' concept of AI as 'simulators' rather than agents, genies, or oracles. He explains how language models like GPT don't have goals or intentions, but simply complete text based on patterns. This applies even to ChatGPT, which simulates a helpful assistant character. Scott then explores the implications for AI alignment and draws parallels to human cognition, suggesting humans may also be prediction engines playing characters shaped by reinforcement. Shorter summary

Scott examines how AI language models' opinions and behaviors evolve as they become more advanced, discussing implications for AI alignment. Longer summary

Scott Alexander analyzes a study on how AI language models' political opinions and behaviors change as they become more advanced and undergo different training. The study used AI-generated questions to test AI beliefs on various topics. Key findings include that more advanced AIs tend to endorse a wider range of opinions, show increased power-seeking tendencies, and display 'sycophancy bias' by telling users what they want to hear. Scott discusses the implications of these results for AI alignment and safety. Shorter summary

Scott Alexander analyzes the shortcomings of OpenAI's ChatGPT, highlighting the limitations of current AI alignment techniques and their implications for future AI development. Longer summary

Scott Alexander discusses the limitations of OpenAI's ChatGPT, focusing on its inability to consistently avoid saying offensive things despite extensive training. He argues that this demonstrates fundamental problems with current AI alignment techniques, particularly Reinforcement Learning from Human Feedback (RLHF). The post outlines three main issues: RLHF's ineffectiveness, potential negative consequences when it does work, and the possibility of more advanced AIs bypassing it entirely. Alexander concludes by emphasizing the broader implications for AI safety and the need for better control mechanisms. Shorter summary