Shows / AI Safety Newsletter
AI Safety Newsletter
Narrations of the AI Safety Newsletter by the Center for AI Safety. We discuss developments in AI and AI safety. No technical background required. This podcast also contains narrations of some of our publications. ABOUT US The Center for AI Safety (CAIS) is a San Francisco-based research and field-building nonprofit. We believe that artificial intelligence has the potential to profoundly benefit the world, provided that we can develop and use it safely. However, in contrast to the dramatic…
Episodes
- AI Safety Newsletter
AISN #27: Defensive Accelerationism
Welcome to the AI Safety Newsletter by the Center for AI Safety. We discuss developments in AI and AI safety. No technical background required. Defensive…
- AI Safety Newsletter
AISN #26: National Institutions for AI Safety
Also, Results From the UK Summit, and New Releases From OpenAI and xAI. Welcome to the AI Safety Newsletter by the Center for AI Safety. We discuss…
- AI Safety Newsletter
AISN #25: White House Executive Order on AI, UK AI Safety Summit, and Progress on Voluntary Evaluations of AI Risks.
Welcome to the AI Safety Newsletter by the Center for AI Safety. We discuss developments in AI and AI safety. No technical background required.White House…
- AI Safety Newsletter
AISN #24: Kissinger Urges US-China Cooperation on AI, China’s New AI Law, US Export Controls, International Institutions, and Open Source AI.
Welcome to the AI Safety Newsletter by the Center for AI Safety. We discuss developments in AI and AI safety. No technical background required.China's New AI…
- AI Safety Newsletter
AISN #23: New OpenAI Models, News from Anthropic, and Representation Engineering.
Welcome to the AI Safety Newsletter by the Center for AI Safety. We discuss developments in AI and AI safety. No technical background required.OpenAI releases…
- AI Safety Newsletter
AISN #21: Google DeepMind’s GPT-4 Competitor, Military Investments in Autonomous Drones, The UK AI Safety Summit, and Case Studies in AI Policy.
Welcome to the AI Safety Newsletter by the Center for AI Safety. We discuss developments in AI and AI safety. No technical background required.Google…
- AI Safety Newsletter
AISN #20: LLM Proliferation, AI Deception, and Continuing Drivers of AI Capabilities.
AI Deception: Examples, Risks, SolutionsAI deception is the topic of a new paper from researchers at and affiliated with the Center for AI Safety. It surveys…
- AI Safety Newsletter
[Paper] “An Overview of Catastrophic AI Risks” by Dan Hendrycks, Mantas Mazeika and Thomas Woodside
Rapid advancements in artificial intelligence (AI) have sparked growing concerns among experts, policymakers, and world leaders regarding the potential for…
- AI Safety Newsletter
[Paper] “Unsolved Problems in ML Safety” by Dan Hendrycks, Nicholas Carlini, John Schulman and Jacob Steinhardt
Machine learning (ML) systems are rapidly increasing in size, are acquiring new capabilities, and are increasingly deployed in high-stakes settings. As with…
- AI Safety Newsletter
[Paper] “X-Risk Analysis for AI Research” by Dan Hendrycks and Mantas Mazeika
Artificial intelligence (AI) has the potential to greatly improve society, but as with any powerful technology, it comes with heightened risks and…
- AI Safety Newsletter
AISN #19: US-China Competition on AI Chips, Measuring Language Agent Developments, Economic Analysis of Language Model Propaganda, and White House AI Cyber Challenge.
US-China Competition on AI ChipsModern AI systems are trained on advanced computer chips which are designed and fabricated by only a handful of companies in…
- AI Safety Newsletter
AISN #18: Challenges of Reinforcement Learning from Human Feedback, Microsoft’s Security Breach, and Conceptual Research on AI Safety.
Challenges of Reinforcement Learning from Human FeedbackIf you’ve used ChatGPT, you might’ve noticed the “thumbs up” and “thumbs down” buttons next to each of…
- AI Safety Newsletter
AISN #17: Automatically Circumventing LLM Guardrails, the Frontier Model Forum, and Senate Hearing on AI Oversight.
Automatically Circumventing LLM GuardrailsLarge language models (LLMs) can generate hazardous information, such as step-by-step instructions on how to create a…
- AI Safety Newsletter
AISN #16: White House Secures Voluntary Commitments from Leading AI Labs, and Lessons from Oppenheimer .
White House Unveils Voluntary Commitments to AI Safety from Leading AI LabsLast Friday, the White House announced a series of voluntary commitments from seven…
- AI Safety Newsletter
AISN #15: China and the US take action to regulate AI, results from a tournament forecasting AI risk, updates on xAI’s plan, and Meta releases its open-source and commercially available Llama 2.
Both China and the US take action to regulate AILast week, regulators in both China and the US took aim at generative AI services. These actions show that…
- AI Safety Newsletter
AISN #14: OpenAI’s ‘Superalignment’ team, Musk’s xAI launches, and developments in military AI use .
OpenAI announces a ‘superalignment’ teamOn July 5th, OpenAI announced the ‘Superalignment’ team: a new research team given the goal of aligning…
- AI Safety Newsletter
AISN #13: An interdisciplinary perspective on AI proxy failures, new competitors to ChatGPT, and prompting language models to misbehave.
Interdisciplinary Perspective on AI Proxy FailuresIn this story, we discuss a recent paper on why proxy goals fail. First, we introduce proxy gaming, and then…
- AI Safety Newsletter
AISN #12: Policy Proposals from NTIA’s Request for Comment, and Reconsidering Instrumental Convergence.
Policy Proposals from NTIA’s Request for CommentThe National Telecommunications and Information Administration publicly requested comments on the matter from…
- AI Safety Newsletter
AISN #11: An Overview of Catastrophic AI Risks.
An Overview of Catastrophic AI RisksGlobal leaders are concerned that artificial intelligence could pose catastrophic risks. 42% of CEOs polled at the Yale CEO…
- AI Safety Newsletter
AISN #10: How AI could enable bioterrorism, and policymakers continue to focus on AI .
How AI could enable bioterrorismOnly a hundred years ago, no person could have single handedly destroyed humanity. Nuclear weapons changed this situation…
- AI Safety Newsletter
AISN #9: Statement on Extinction Risks, Competitive Pressures, and When Will AI Reach Human-Level? .
Top Scientists Warn of Extinction Risks from AILast week, hundreds of AI scientists and notable public figures signed a public statement on AI risks written by…
- AI Safety Newsletter
AISN #8: Why AI could go rogue, how to screen for AI risks, and grants for research on democratic governance of AI.
Yoshua Bengio makes the case for rogue AIAI systems pose a variety of different risks. Renowned AI scientist Yoshua Bengio recently argued for one particularly…
- AI Safety Newsletter
AISN #7: Disinformation, recommendations for AI labs, and Senate hearings on AI.
How AI enables disinformationYesterday, a fake photo generated by an AI tool showed an explosion at the Pentagon. The photo was falsely attributed to Bloomberg…
- AI Safety Newsletter
AISN #6: Examples of AI safety progress, Yoshua Bengio proposes a ban on AI agents, and lessons from nuclear arms control .
Examples of AI safety progressTraining AIs to behave safely and beneficially is difficult. They might learn to game their reward function, deceive human…
- AI Safety Newsletter
AISN #5: Geoffrey Hinton speaks out on AI risk, the White House meets with AI labs, and Trojan attacks on language models.
Geoffrey Hinton is concerned about existential risks from AIGeoffrey Hinton won the Turing Award for his work on AI. Now he says that part of him regrets his…
- AI Safety Newsletter
AISN #4: AI and cybersecurity, persuasive AIs, weaponization, and Hinton talks AI risks.
Cybersecurity Challenges in AI SafetyMeta accidentally leaks a language model to the public. Meta’s newest language model, LLaMa, was publicly leaked online…
- AI Safety Newsletter
AISN #3: AI policy proposals and a new challenger approaches.
Policy Proposals for AI SafetyCritical industries rely on the government to protect consumer safety. The FAA approves new airplane designs, the FDA tests new…
- AI Safety Newsletter
AISN #2: ChaosGPT and the rise of language model agents, evolutionary pressures and AI, AI safety in the media.
ChaosGPT and the Rise of Language AgentsChatbots like ChatGPT usually only respond to one prompt at a time, and a human user must provide a new prompt to get a…
- AI Safety Newsletter
AISN #1: Public opinion on AI, plugging ChatGPT into the internet, and the economic impacts of language models..
Growing concerns about rapid AI progressRecent advancements in AI have thrust it into the center of attention. What do people think about the risks of AI?The…