mechanistic interpretability
New research goes beyond behavioral analysis to trace the internal mechanisms LLMs use when weighing competing reward signals, offering insights into AI decision-making at the circuit level.
LLM Interpretability
New research introduces ADAPT, a hybrid optimization technique that combines discrete and continuous methods to visualize and understand internal features of large language models.
AI Agents
New research systematically documents technical and safety features across deployed agentic AI systems, creating a comprehensive index for understanding how autonomous AI operates in the wild.
machine unlearning
New research explores machine unlearning for LLM agents, addressing how autonomous AI systems can selectively forget data while maintaining tool-use and reasoning capabilities.
AI Agents
Technical guide to implementing traceable AI decision-making with comprehensive audit logging and human oversight checkpoints for accountable autonomous systems.
AI Security
Security researchers demonstrate how hidden prompt injections in code repositories can hijack AI coding agents like Cline, exposing critical vulnerabilities in agentic AI systems.
AI safety
From RLHF to Constitutional AI, these four technical approaches aim to prevent AI systems from lying, manipulating, or causing harm—critical foundations for trustworthy synthetic media.
AI Ethics
New research introduces Mirror, a multi-agent framework using AI to assist in ethics review processes, potentially transforming how AI systems evaluate content for safety and compliance.
LLM research
Researchers propose a novel framework for visualizing and benchmarking factual hallucinations in large language models by analyzing internal neural activations and clustering patterns.
Anthropic
Anthropic raises $30 billion in Series G funding, reaching a $380 billion valuation. The massive investment signals continued confidence in frontier AI development.
machine unlearning
New research introduces a principled approach to removing harmful concepts from generative AI models using tempering and classifier guidance, with major implications for synthetic media safety.
AI safety
New research examines how AI communities are splitting on human control approaches for autonomous agents, finding significant divergence in oversight philosophies that could shape the future of AI governance.