LessWrong (Curated & Popular)

Nate Soares discusses the shift in focus from understanding minds to building empirical understanding of modern AIs. The podcast explores the obstacles to aligning smarter than human AI and the importance of interpretability research. It also highlights the challenges of differentiating genuine solutions from superficial ones and the need for a comprehensive scientific understanding of AI.

This podcast discusses the importance of responsible scaling policies in AI development and how they can reduce risk. The podcast emphasizes that voluntary commitments are not enough and that regulation is necessary to ensure a higher degree of safety. Transparency and debate around responsible scaling policies can help improve regulation. The podcast also explores the role of responsible scaling policies in informing effective regulation and promoting safe development practices.

The podcast discusses the dangers of developing AI, including loss of control, an AI rights movement, impact on human labor value, use in warfare, and the need for responsible scaling policies. The speaker reflects on their involvement in the AI debate, expressing concerns about competence and safety in handling the transition to machine superintelligence. They advocate for halting AI development and highlight the global risks of non-deceptive, smarter-than-human intelligences.

The podcast explores the challenges of aligning AI with human values and the concept of corrigible AI. It discusses the potential and limitations of Language Model Agents (LLMs) and the repetition trap phenomenon. A debate ensues about the implications of AI alignment challenges and the risks of misgeneralized obedience in AI. Overall, it delves into the complex and evolving field of AI alignment.

Simon Lermen and Jeffrey Ladish discuss LoRA fine-tuning and its impact on safety training. They explore the effectiveness of safety procedures, the QloRA technique, dark topics of slurs and brutal killings, effects of model size on harmful task performance, a hypothetical plan for AI attack and control, and the analysis of refusals and comparison of instruction sets.

Holly Elmore, organizer of AI Pause protests, and Rob Miles, AI Safety YouTuber, explore the effectiveness of protests, the role of activists in technological advancements, the misconception of technical work, the clash between advocacy and truth-seeking, the importance of rationality, and the significance of advocacy in AI safety.

The podcast discusses the importance of transparency in AI labs building AGI, stressing the need to communicate risks to the public and policy makers.

The podcast discusses sum-threshold attacks and the importance of coordinated arguments. It explores adversarial image attacks and how small changes can deceive AI classifiers. The concept of optimization channels and the notion of a vector space representing noticeable features are also explored.

This podcast discusses the potential of gene drives to end malaria and the need for deployment to save lives. It explores the technical details of gene drive construction, ordering DNA, setting up mosquito breeding facilities, implementing gene drives to combat malaria, and overcoming political barriers in Africa.

This podcast explores the importance of Responsible Scaling Policies (RSBs) in preventing AI existential risk and emphasizes the need for public support. It discusses the concepts of capabilities evaluation, safety evaluation, and the role of RSP commitments in ensuring AI safety. The significance of mechanistic interpretability and leveraging influence in AI models is also explored. The effectiveness of a labs-first approach in progressing AI technology and the importance of RSBs are discussed. The podcast advocates for robust safety precautions (RSPs) in AI development, highlighting their concrete and actionable nature compared to advocating for a pause in development.