Picture for Markus Anderljung

Markus Anderljung

IDs for AI Systems

Add code
Jun 17, 2024
Viaarxiv icon

Beyond static AI evaluations: advancing human interaction evaluations for LLM harms and risks

Add code
May 17, 2024
Viaarxiv icon

Societal Adaptation to Advanced AI

Add code
May 16, 2024
Figure 1 for Societal Adaptation to Advanced AI
Figure 2 for Societal Adaptation to Advanced AI
Figure 3 for Societal Adaptation to Advanced AI
Viaarxiv icon

Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Add code
Apr 15, 2024
Viaarxiv icon

Responsible Reporting for Frontier AI Development

Add code
Apr 03, 2024
Viaarxiv icon

Visibility into AI Agents

Add code
Feb 04, 2024
Viaarxiv icon

Towards Publicly Accountable Frontier LLMs: Building an External Scrutiny Ecosystem under the ASPIRE Framework

Add code
Nov 15, 2023
Figure 1 for Towards Publicly Accountable Frontier LLMs: Building an External Scrutiny Ecosystem under the ASPIRE Framework
Figure 2 for Towards Publicly Accountable Frontier LLMs: Building an External Scrutiny Ecosystem under the ASPIRE Framework
Viaarxiv icon

Frontier AI Regulation: Managing Emerging Risks to Public Safety

Add code
Jul 11, 2023
Figure 1 for Frontier AI Regulation: Managing Emerging Risks to Public Safety
Figure 2 for Frontier AI Regulation: Managing Emerging Risks to Public Safety
Figure 3 for Frontier AI Regulation: Managing Emerging Risks to Public Safety
Figure 4 for Frontier AI Regulation: Managing Emerging Risks to Public Safety
Viaarxiv icon

Model evaluation for extreme risks

Add code
May 24, 2023
Figure 1 for Model evaluation for extreme risks
Figure 2 for Model evaluation for extreme risks
Figure 3 for Model evaluation for extreme risks
Figure 4 for Model evaluation for extreme risks
Viaarxiv icon

Protecting Society from AI Misuse: When are Restrictions on Capabilities Warranted?

Add code
Mar 29, 2023
Figure 1 for Protecting Society from AI Misuse: When are Restrictions on Capabilities Warranted?
Viaarxiv icon