Picture for Markus Anderljung

Markus Anderljung

Infrastructure for AI Agents

Add code
Jan 17, 2025
Figure 1 for Infrastructure for AI Agents
Figure 2 for Infrastructure for AI Agents
Figure 3 for Infrastructure for AI Agents
Figure 4 for Infrastructure for AI Agents
Viaarxiv icon

IDs for AI Systems

Add code
Jun 17, 2024
Figure 1 for IDs for AI Systems
Figure 2 for IDs for AI Systems
Figure 3 for IDs for AI Systems
Figure 4 for IDs for AI Systems
Viaarxiv icon

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

Add code
May 17, 2024
Figure 1 for Beyond static AI evaluations: advancing human interaction evaluations for LLM harms and risks
Figure 2 for Beyond static AI evaluations: advancing human interaction evaluations for LLM harms and risks
Figure 3 for Beyond static AI evaluations: advancing human interaction evaluations for LLM harms and risks
Figure 4 for Beyond static AI evaluations: advancing human interaction evaluations for LLM harms and risks
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
Figure 1 for Foundational Challenges in Assuring Alignment and Safety of Large Language Models
Figure 2 for Foundational Challenges in Assuring Alignment and Safety of Large Language Models
Figure 3 for Foundational Challenges in Assuring Alignment and Safety of Large Language Models
Figure 4 for Foundational Challenges in Assuring Alignment and Safety of Large Language Models
Viaarxiv icon

Responsible Reporting for Frontier AI Development

Add code
Apr 03, 2024
Figure 1 for Responsible Reporting for Frontier AI Development
Figure 2 for Responsible Reporting for Frontier AI Development
Figure 3 for Responsible Reporting for Frontier AI Development
Figure 4 for Responsible Reporting for Frontier AI Development
Viaarxiv icon

Visibility into AI Agents

Add code
Feb 04, 2024
Figure 1 for Visibility into AI Agents
Figure 2 for Visibility into AI Agents
Viaarxiv icon

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

Add code
Nov 15, 2023
Viaarxiv icon

Frontier AI Regulation: Managing Emerging Risks to Public Safety

Add code
Jul 11, 2023
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