BlueDot Narrated
Episodes
Accelerating Vaccine Development: The 100 Days Mission
14 Dec 2025
Contributed by Lukas
Audio versions of blogs and papers from BlueDot courses. Original text: https://www.ncbi.nlm.nih.gov/books/NBK614029/ Author(s): Aishani Aatresh, N...
Day Zero Antivirals for Future Pandemics
14 Dec 2025
Contributed by Lukas
Audio versions of blogs and papers from BlueDot courses. Original Text: https://press.asimov.com/articles/antiviralsAuthor(s): Brian WangA podcast by...
Biosecurity and the Goals of This Course
05 Dec 2025
Contributed by Lukas
This introduction to the course underscores its focus on mitigating the risk of catastrophic pandemics, a specific aspect of the complex and multidisc...
High-Risk Human-Caused Pathogen Exposure Events From 1975-2016
05 Dec 2025
Contributed by Lukas
This table documents the known human-caused pathogen exposure events from 1975-2016, both accidental and deliberate, from peaceful research and biowea...
Info Hazard Guidance for Biosecurity Discussions
05 Dec 2025
Contributed by Lukas
This document introduces the concept of information hazards (often called 'info hazards') and reasoning for why we should be cautious around...
Understanding AI-Facilitated Biological Weapon Development
05 Dec 2025
Contributed by Lukas
This report breaks down the categorisation of LLMs and BDTs into more specific subcategories of AI-enabled biological tools at each stage of the risk ...
Artificial Intelligence and Biological Misuse: Differentiating Risks of Language Models and Biological Design Tools
05 Dec 2025
Contributed by Lukas
This paper proposes two categories of AI models that could have impacts on biosecurity in different ways: large language models (LLMs) and biological ...
We’re Entering a Golden Age of Engineering Biology
05 Dec 2025
Contributed by Lukas
Historically, the complexity and unpredictability of biology has meant most scientific progress in this field has come from slow and expensive trial-a...
Dual Use Research of Concern in the Life Sciences: Current Issues and Controversies
05 Dec 2025
Contributed by Lukas
There is a tension in the life sciences between scientific transparency and the need for secrecy to protect national or global security. This report i...
Pandemic Prevention as Fire-Fighting
05 Dec 2025
Contributed by Lukas
This article introduces a range of strategies to reduce pandemic risk whilst drawing parallels to fire-fighting interventions. It argues that pandemic...
The Danger of ‘Invisible’ Biolabs Across the U.S.
05 Dec 2025
Contributed by Lukas
As synthetic biology techniques develop and the barriers to entry become lower, we are increasingly seeing the development of privately-operated biolo...
Want to Prevent Pandemics? Stop Spillovers
05 Dec 2025
Contributed by Lukas
This article proposes four key actions that can be taken to prevent outbreaks from zoonotic spillover: protecting tropical forests, regulating or bann...
Addressing the Gap in International Norms for Biosafety
05 Dec 2025
Contributed by Lukas
The document highlights the need for national-level norms for biosafety, given that a laboratory accident with contagious pathogens could have global ...
Research Involving Enhanced Potential Pandemic Pathogens
05 Dec 2025
Contributed by Lukas
This page gives a brief overview of the NIH's framework for guiding funding decisions on potentially risky research involving enhanced potential ...
Biological Weapons Convention
05 Dec 2025
Contributed by Lukas
This Wikipedia article provides an overview of the Biological Weapons Convention, a disarmament treaty that bans the development, production, acquisit...
Preventing the Misuse of DNA Synthesis
05 Dec 2025
Contributed by Lukas
DNA synthesis represents the primary interface between the digital and physical worlds when it comes to synthetic biology - the point at which potenti...
Common Terminology in Infectious Disease Epidemiology
05 Dec 2025
Contributed by Lukas
This resource provides a brief introduction to some of the most common terms used in infectious disease epidemiology.Original text:https://docs.google...
Toward a Global Pathogen Early Warning System
05 Dec 2025
Contributed by Lukas
This report covers the current landscape in pathogen early warning and biosurveillance, highlights challenges and identifies opportunities from emergi...
Nowcasting Epidemics of Novel Pathogens: Lessons from COVID-19
05 Dec 2025
Contributed by Lukas
This paper discusses critical questions for gaining early situational awareness in an outbreak, using COVID-19 as an example. It highlights key querie...
Emerging COVID-19 Success Story: Vietnam's Commitment to Containment
04 Dec 2025
Contributed by Lukas
Despite sharing a land border with China, Vietnam mounted one of the strongest early responses to COVID-19, reporting only 35 deaths by December 31, 2...
What Were the Death Tolls from Pandemics in History?
04 Dec 2025
Contributed by Lukas
This resource from 'Our World in Data' estimates the death tolls from the most devastating pandemics in history, with a particular focus on ...
The New Bioweapons: How Synthetic Biology Could Destabilize the World
04 Dec 2025
Contributed by Lukas
Original text: https://drive.google.com/file/d/19dxfYiUnrK4fR5EJW3Nb2zkpgvsEC28y/view?usp=sharingAuthor(s): Roger Brent, T. Greg McKelvey, Jr., and Ja...
We Aren't Prepared for the Next Pandemic
04 Dec 2025
Contributed by Lukas
It will probably start with a cluster of unusual symptoms. Some of the people with the disease will know each other, but won’t have been exposed to ...
The Worst Covid Strategy Was Not Picking One
04 Dec 2025
Contributed by Lukas
Original text:https://www.bloomberg.com/graphics/2023-opinion-lessons-learned-from-covid-pandemic-global-comparison/Author(s):Bloomberg OpinionA podca...
COVID-19: Examining the Effectiveness of Non-Pharmaceutical Interventions
04 Dec 2025
Contributed by Lukas
Original text:https://royalsociety.org/-/media/policy/projects/impact-non-pharmaceutical-interventions-on-covid-19-transmission/covid-19-examining-the...
From Warp Speed to 100 Days
04 Dec 2025
Contributed by Lukas
"During the COVID pandemic, we learned to design vaccines within weeks. Now, the bottleneck is testing that they work. To get even faster, we nee...
Indoor Air Quality Is the Next Great Public Health Challenge
04 Dec 2025
Contributed by Lukas
"Cleaner indoor air can increase productivity, improve student outcomes, and prevent pandemics."Original text: https://ifp.org/indoor-air-qu...
Towards a Theory of Pandemic-Proof PPE
04 Dec 2025
Contributed by Lukas
"Vital workers must be protected against viral threats so that critical functions of society can continue during a global pandemic. Globally, COV...
Broad-Spectrum Antiviral Agents: A Crucial Pandemic Tool
04 Dec 2025
Contributed by Lukas
Original text: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7103698/Author(s): Amesh Adalja and Thomas InglesbyA podcast by BlueDot Impact.Learn more ...
ESM3: Simulating 500 Million Years of Evolution with a Language Model
04 Dec 2025
Contributed by Lukas
ESM3 is an AI model which is trained on protein sequence, structure and function data. This allows it to follow prompts to design novel proteins. When...
Differential Technology Development: An Innovation Governance Consideration for Navigating Technology Risks
04 Dec 2025
Contributed by Lukas
This paper introduces a framing of "differential technology development" – affecting the relative timing of new innovations to reduce a sp...
A Framework for Technical Progress on Biosecurity
04 Dec 2025
Contributed by Lukas
In this post, Kyle Fish presents five key goals for biosecurity technologies: to be fast, general, cheap, robust, and scalable. These will be useful h...
The Biological Weapons Convention: An Introduction
04 Dec 2025
Contributed by Lukas
This resource provides an overview of the Biological Weapons Convention, a disarmament treaty that bans the development, production, acquisition, tran...
Adherence to and Compliance with Arms Control, Nonproliferation, and Disarmament Agreements and Commitments
04 Dec 2025
Contributed by Lukas
The US State Department report is released each April and provides an assessment of states' adherence to arms control, non-proliferation and disa...
AI and Leviathan: Part I
29 Sep 2025
Contributed by Lukas
By Samuel HammondSource: https://www.secondbest.ca/p/ai-and-leviathan-part-iA podcast by BlueDot Impact.Learn more on the AI Safety Fundamentals websi...
d/acc: One Year Later
19 Sep 2025
Contributed by Lukas
By Vitalik ButerinEthereum founder Vitalik Buterin describes how democratic, defensive and decentralised technologies could distribute AI's power...
A Playbook for Securing AI Model Weights
18 Sep 2025
Contributed by Lukas
By Sella Nevo et al.In this report, RAND researchers identify real-world attack methods that malicious actors could use to steal AI model weights. The...
AI Emergency Preparedness: Examining the Federal Government's Ability to Detect and Respond to AI-Related National Security Threats
18 Sep 2025
Contributed by Lukas
By Akash Wasil et al.This paper uses scenario planning to show how governments could prepare for AI emergencies. The authors examine three plausible d...
The Project: Situational Awareness
18 Sep 2025
Contributed by Lukas
By Leopold AschenbrennerA former OpenAI researcher argues that private AI companies cannot safely develop superintelligence due to security vulnerabil...
Resilience and Adaptation to Advanced AI
18 Sep 2025
Contributed by Lukas
By Jamie BernardiJamie Bernardi argues that we can't rely solely on model safeguards to ensure AI safety. Instead, he proposes "AI resilienc...
Introduction to AI Control
18 Sep 2025
Contributed by Lukas
By Sarah Hastings-WoodhouseAI Control is a research agenda that aims to prevent misaligned AI systems from causing harm. It is different from AI align...
Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?
18 Sep 2025
Contributed by Lukas
By Yoshua Bengio et al.This paper argues that building generalist AI agents poses catastrophic risks, from misuse by bad actors to a potential loss of...
The Intelligence Curse
18 Sep 2025
Contributed by Lukas
By Luke Drago and Rudolf LaineThis section explores how the arrival of AGI could trigger an “intelligence curse,” where automation of all work rem...
AI Is Reviving Fears Around Bioterrorism. What’s the Real Risk?
12 Sep 2025
Contributed by Lukas
By Kyle HiebertThe global spread of large language models is heightening concerns that extremists could leverage AI to develop or deploy biological we...
AI and the Evolution of Biological National Security Risks
12 Sep 2025
Contributed by Lukas
By Bill Drexel and Caleb WithersThis report considers how rapid AI advancements could reshape biosecurity risks, from bioterrorism to engineered super...
The Intelligence Curse (Sections 1-3)
12 Sep 2025
Contributed by Lukas
By Luke Drago and Rudolf LaineThis piece explores key arguments from sections 3 and 4 of The Intelligence Curse, continuing the authors’ analysis ...
The Most Important Time in History Is Now
09 Sep 2025
Contributed by Lukas
By Tomas PueyoThis blog post traces AI's rapid leap from high school to PhD-level intelligence in just two years, examines whether physical bottl...
Why Do People Disagree About When Powerful AI Will Arrive?
09 Sep 2025
Contributed by Lukas
By Sarah Hastings-WoodhouseMost experts agree that AGI is possible. They also agree that it will have transformative consequences. There is less conse...
Governance of Superintelligence
09 Sep 2025
Contributed by Lukas
By Sam Altman, Greg Brockman, Ilya SutskeverOpenAI's leadership outline how humanity might govern superintelligence, proposing international over...
Scaling: The State of Play in AI
09 Sep 2025
Contributed by Lukas
By Ethan MollickThis post explains the "scaling laws" that drive rapid AI progress: when you make AI models bigger and train them with more ...
Measuring AI Ability to Complete Long Tasks
09 Sep 2025
Contributed by Lukas
By Thomas Kwa et al.We propose measuring AI performance in terms of the length of tasks AI agents can complete. We show that this metric has been cons...
The AI Revolution: The Road to Superintelligence
08 Sep 2025
Contributed by Lukas
By Tim UrbanTim Urban uses historical analogies to show why AI progress might accelerate much faster than we expect, and how AI systems could rapidly ...
"Long" Timelines to Advanced AI Have Gotten Crazy Short
08 Sep 2025
Contributed by Lukas
By Helen TonerHelen Toner, former OpenAI board member, reveals how the AI timeline debate has compressed: even conservative experts who once dismissed...
Preparing for Launch
03 Sep 2025
Contributed by Lukas
By Tim Fist, Tao Burga, and Tim HwangThe Institute for Progress lays out how the US Government could shape the development of AI towards human flouris...
In Search of a Dynamist Vision for Safe Superhuman AI
03 Sep 2025
Contributed by Lukas
By Helen TonerThis essay describes AI safety policies that rely on centralised control (surveillance, fewer AI projects, licensing regimes) as "s...
It’s Practically Impossible to Run a Big AI Company Ethically
03 Sep 2025
Contributed by Lukas
By Sigal Samuel (Vox Future Perfect)Even "safety-first" AI companies like Anthropic face market pressure that can override ethical commitmen...
Seeking Stability in the Competition for AI Advantage
03 Sep 2025
Contributed by Lukas
By Iskander Rehman, Karl P. Mueller, Michael J. MazarrThis RAND article describes some of the international dynamics driving the race to AGI between t...
Solarpunk: A Vision for a Sustainable Future
03 Sep 2025
Contributed by Lukas
By Joshua KrookWhat might sustainable human progress look like, beyond pure technological acceleration? This essay provides an alternative vision, bas...
The Gentle Singularity
03 Sep 2025
Contributed by Lukas
By Sam AltmanThis blog post offers a vivid, optimistic vision of rapid AI progress from the CEO of OpenAI. Altman suggests that the accelerating techn...
AI-Enabled Coups: How a Small Group Could Use AI to Seize Power
30 Aug 2025
Contributed by Lukas
By Tom Davidson, Lukas Finnveden and Rose Hadshar. The development of AI that is more broadly capable than humans will create a new and serious threa...
Progress on Causal Influence Diagrams
04 Jan 2025
Contributed by Lukas
By Tom Everitt, Ryan Carey, Lewis Hammond, James Fox, Eric Langlois, and Shane LeggAbout 2 years ago, we released the first few papers on understandin...
Careers in Alignment
04 Jan 2025
Contributed by Lukas
Richard Ngo compiles a number of resources for thinking about careers in alignment research.Original text:https://docs.google.com/document/d/1iFszDulg...
Cooperation, Conflict, and Transformative Artificial Intelligence: Sections 1 & 2 — Introduction, Strategy and Governance
04 Jan 2025
Contributed by Lukas
Transformative artificial intelligence (TAI) may be a key factor in the long-run trajectory of civilization. A growing interdisciplinary community has...
Logical Induction (Blog Post)
04 Jan 2025
Contributed by Lukas
MIRI is releasing a paper introducing a new model of deductively limited reasoning: “Logical induction,” authored by Scott Garrabrant, Tsvi Benson...
Embedded Agents
04 Jan 2025
Contributed by Lukas
Suppose you want to build a robot to achieve some real-world goal for you—a goal that requires the robot to learn for itself and figure out a lot of...
Understanding Intermediate Layers Using Linear Classifier Probes
04 Jan 2025
Contributed by Lukas
Abstract:Neural network models have a reputation for being black boxes. We propose to monitor the features at every layer of a model and measure how s...
Feature Visualization
04 Jan 2025
Contributed by Lukas
There is a growing sense that neural networks need to be interpretable to humans. The field of neural network interpretability has formed in response ...
Acquisition of Chess Knowledge in Alphazero
04 Jan 2025
Contributed by Lukas
Abstract:What is learned by sophisticated neural network agents such as AlphaZero? This question is of both scientific and practical interest. If the ...
Takeaways From Our Robust Injury Classifier Project [Redwood Research]
04 Jan 2025
Contributed by Lukas
With the benefit of hindsight, we have a better sense of our takeaways from our first adversarial training project (paper). Our original aim was to us...
High-Stakes Alignment via Adversarial Training [Redwood Research Report]
04 Jan 2025
Contributed by Lukas
(Update: We think the tone of this post was overly positive considering our somewhat weak results. You can read our latest post with more takeaways an...
Introduction to Logical Decision Theory for Computer Scientists
04 Jan 2025
Contributed by Lukas
Decision theories differ on exactly how to calculate the expectation--the probability of an outcome, conditional on an action. This foundational dif...
Debate Update: Obfuscated Arguments Problem
04 Jan 2025
Contributed by Lukas
This is an update on the work on AI Safety via Debate that we previously wrote about here. What we did: We tested the debate protocol introduced in ...
Robust Feature-Level Adversaries Are Interpretability Tools
04 Jan 2025
Contributed by Lukas
Abstract: The literature on adversarial attacks in computer vision typically focuses on pixel-level perturbations. These tend to be very difficult to...
AI Safety via Red Teaming Language Models With Language Models
04 Jan 2025
Contributed by Lukas
Abstract: Language Models (LMs) often cannot be deployed because of their potential to harm users in ways that are hard to predict in advance. Prior ...
AI Safety via Debate
04 Jan 2025
Contributed by Lukas
Abstract:To make AI systems broadly useful for challenging real-world tasks, we need them to learn complex human goals and preferences. One approach t...
Least-To-Most Prompting Enables Complex Reasoning in Large Language Models
04 Jan 2025
Contributed by Lukas
Chain-of-thought prompting has demonstrated remarkable performance on various natural language reasoning tasks. However, it tends to perform poorly on...
Summarizing Books With Human Feedback
04 Jan 2025
Contributed by Lukas
To safely deploy powerful, general-purpose artificial intelligence in the future, we need to ensure that machine learning models act in accordance wit...
Supervising Strong Learners by Amplifying Weak Experts
04 Jan 2025
Contributed by Lukas
Abstract: Many real world learning tasks involve complex or hard-to-specify objectives, and using an easier-to-specify proxy can lead to poor perform...
Measuring Progress on Scalable Oversight for Large Language Models
04 Jan 2025
Contributed by Lukas
Abstract: Developing safe and useful general-purpose AI systems will require us to make progress on scalable oversight: the problem of supervising sy...
Is Power-Seeking AI an Existential Risk?
04 Jan 2025
Contributed by Lukas
This report examines what I see as the core argument for concern about existential risk from misaligned artificial intelligence. I proceed in two stag...
Yudkowsky Contra Christiano on AI Takeoff Speeds
04 Jan 2025
Contributed by Lukas
In 2008, thousands of blog readers - including yours truly, who had discovered the rationality community just a few months before - watched Robin Hans...
Why AI Alignment Could Be Hard With Modern Deep Learning
04 Jan 2025
Contributed by Lukas
Why would we program AI that wants to harm us? Because we might not know how to do otherwise.Source:https://www.cold-takes.com/why-ai-alignment-could-...
AGI Ruin: A List of Lethalities
04 Jan 2025
Contributed by Lukas
I have several times failed to write up a well-organized list of reasons why AGI will kill you. People come in with different ideas about why AGI woul...
Where I Agree and Disagree with Eliezer
04 Jan 2025
Contributed by Lukas
(Partially in response to AGI Ruin: A list of Lethalities. Written in the same rambling style. Not exhaustive.)Agreements Powerful AI systems have a g...
ML Systems Will Have Weird Failure Modes
04 Jan 2025
Contributed by Lukas
Previously, I've argued that future ML systems might exhibit unfamiliar, emergent capabilities, and that thought experiments provide one approach...
Thought Experiments Provide a Third Anchor
04 Jan 2025
Contributed by Lukas
Previously, I argued that we should expect future ML systems to often exhibit "emergent" behavior, where they acquire new capabilities that ...
Goal Misgeneralisation: Why Correct Specifications Aren’t Enough for Correct Goals
04 Jan 2025
Contributed by Lukas
As we build increasingly advanced AI systems, we want to make sure they don’t pursue undesired goals. This is the primary concern of the AI alignmen...
Deceptively Aligned Mesa-Optimizers: It’s Not Funny if I Have to Explain It
04 Jan 2025
Contributed by Lukas
Our goal here is to popularize obscure and hard-to-understand areas of AI alignment.So let’s try to understand the incomprehensible meme! Our main ...
What Failure Looks Like
04 Jan 2025
Contributed by Lukas
Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.The stereotyped image of AI catastrophe is a powerful, malicious...
Learning From Human Preferences
04 Jan 2025
Contributed by Lukas
One step towards building safe AI systems is to remove the need for humans to write goal functions, since using a simple proxy for a complex goal, or ...
Specification Gaming: The Flip Side of AI Ingenuity
04 Jan 2025
Contributed by Lukas
Specification gaming is a behaviour that satisfies the literal specification of an objective without achieving the intended outcome. We have all had e...
Superintelligence: Instrumental Convergence
04 Jan 2025
Contributed by Lukas
According to the orthogonality thesis, intelligent agents may have an enormous range of possible final goals. Nevertheless, according to what we may t...
The Easy Goal Inference Problem Is Still Hard
04 Jan 2025
Contributed by Lukas
One approach to the AI control problem goes like this:Observe what the user of the system says and does.Infer the user’s preferences.Try to make the...
The Alignment Problem From a Deep Learning Perspective
04 Jan 2025
Contributed by Lukas
Within the coming decades, artificial general intelligence (AGI) may surpass human capabilities at a wide range of important tasks. We outline a case ...
AGI Safety From First Principles
04 Jan 2025
Contributed by Lukas
This report explores the core case for why the development of artificial general intelligence (AGI) might pose an existential threat to humanity. It s...
Four Background Claims
04 Jan 2025
Contributed by Lukas
MIRI’s mission is to ensure that the creation of smarter-than-human artificial intelligence has a positive impact. Why is this mission important, an...
Biological Anchors: A Trick That Might Or Might Not Work
04 Jan 2025
Contributed by Lukas
I've been trying to review and summarize Eliezer Yudkowksy's recent dialogues on AI safety. Previously in sequence: Yudkowsky Contra Ngo On ...
A Short Introduction to Machine Learning
04 Jan 2025
Contributed by Lukas
Despite the current popularity of machine learning, I haven’t found any short introductions to it which quite match the way I prefer to introduce pe...
More Is Different for AI
04 Jan 2025
Contributed by Lukas
Machine learning is touching increasingly many aspects of our society, and its effect will only continue to grow. Given this, I and many others care a...
Future ML Systems Will Be Qualitatively Different
04 Jan 2025
Contributed by Lukas
In 1972, the Nobel prize-winning physicist Philip Anderson wrote the essay "More Is Different". In it, he argues that quantitative changes c...