Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Archive Layout with Content
Posts by Category
Posts by Collection
CV
Mentoring
Page not in menu
Page Archive
Portfolio
Blog
Publications
Sitemap
Posts by Tags
Talk map
Talks and presentations
Teaching
Terms and Privacy Policy
Blog posts
Jupyter notebook markdown generator
Posts
How Durable is Our Visibility into AI Cyberattacks?
Our ability to monitor AI-enabled cyberattacks may be far more fragile than it looks. Today we get useful signal about how attackers use AI, but much of that visibility could erode as adversaries grow more sophisticated and move off detectable channels.
Will we get automated alignment research before an AI Takeoff?
AI may automate large parts of AI R&D within the next decade, dramatically accelerating progress. A crucial question for existential risk is the ordering: will automation speed up capabilities research or safety research first? If capabilities race ahead while safety lags, we could find ourselves with very powerful...
Should the AI Safety Community Prioritize Safety Cases?
I recently wrote an Introduction to AI Safety Cases. It left me wondering whether they are actually an impactful intervention that should be prioritized by the AI Safety Community.
Safety Cases Explained: How to Argue an AI is Safe
Safety Cases are a promising approach in AI Governance inspired by other safety-critical industries. They are structured arguments, based on evidence, that a system is safe in a specific context. I will introduce what Safety Cases are, how they can be used, and what work is being done...
A Call for Better Risk Modelling
TL;DR: The EU’s Code of Practice (CoP) mandates AI companies to conduct state-of-the-art Risk Modelling. However, the current SoTA is has severe flaws. By creating risk models and improving methodology, we can enhance the quality of risk management performed by AI companies. This is a neglected area, hence...
Learning from the Luddites: Implications for a modern AI labour movement
The Luddites were a social movement of English textile workers in the 19th century, famous for smashing the machines that were replacing their jobs. The term Luddite is now used to describe opponents of new technologies (often in a derogatory way). However, I believe many people using the...
15 Levers for influencing Frontier AI Companies
The development of AGI could be the most important event of our lifetimes. Ensuring that AI is developed and deployed safely could be the most impactful thing many of us can work on. However, the development of Frontier AI systems is happening in only a handful of companies....
Open Challenges in Representation Engineering
This post summarizes the taxonomy, challenges, and opportunities from a survey paper on Representation Engineering that I’ve written with Sahar Abdelnabi, David Krueger, and Mario Fritz. Cross posted from the AI Alignment Forum
portfolio
Portfolio item number 1
Short description of portfolio item number 1
Portfolio item number 2
Short description of portfolio item number 2
publications
On robust vs fast solving of qualitative constraints
This paper introduces the notion of Robustness to Qualitative Constraint Networks and finds a tradeoff between speed and robustness in heuristics for solving QCNs.
Explaining Learned Reward Functions with Counterfactual Trajectories
We propose a method for explaining reward functions by showing the rewards given to counterfactual trajectories.
Immunization against harmful fine-tuning attacks
LLMs can be fine-tuned with harmful data to remove their safeguards. We formalize the problem and set out conditions for a solution.
Representation Noising: A Defence Mechanism Against Harmful Finetuning
We propose Representation Noising which prevents harmful fine-tuning by removing harmful representations.
Position: Safety Must Precede the Deployment of Open-Ended AI Agents
Open-ended AI is a growing paradigm where AI continuously explores novel and interesting artifacts. This position paper describes specific safety challenges in Open-Ended AI and how they can be mitigated.
Taxonomy, Opportunities, and Challenges of Representation Engineering for Large Language Models
This survey paper reviews the literature on Representation Engineering, a technique for controlling LLMs through their internal representations. We set out a unifying taxonomy, describe methods and applications and showcase weaknesses and opportunities.
Detecting Offensive Cyber Agents: A Detection-in-Depth Approach
AI agents can now orchestrate cyberattacks, increasing their speed, scale, and autonomy while lowering costs. This report frames the offensive cyber agent detection challenge, introduces detection-in-depth as a strategic framework for policymakers and defenders, and proposes five concrete detection mechanisms.
talks
Talk 1 on Relevant Topic in Your Field
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Tutorial 1 on Relevant Topic in Your Field
More information here
Talk 2 on Relevant Topic in Your Field
More information here
Conference Proceeding talk 3 on Relevant Topic in Your Field
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
This is a description of a teaching experience. You can use markdown like any other post.