AI Agents
New research proposes combining blockchain monitoring with agentic AI to create verifiable perception-reasoning-action pipelines, addressing critical trust and authenticity challenges in autonomous AI systems.
AI Safety
Researchers introduce a new evaluation framework for measuring when and how autonomous AI agents violate safety constraints while pursuing objectives, addressing critical gaps in AI alignment research.
AI Safety
New research bridges efficiency and safety by developing formal verification methods for neural networks with early exits, enabling mathematically proven safety guarantees for adaptive AI systems.
LLM Interpretability
New research maps LLM internal representations to brain-derived axes, enabling interpretable reading and targeted steering of model behavior without fine-tuning.
LLM Security
New research reveals how adversarial control tokens can manipulate LLM-as-a-Judge systems into completely reversing their binary decisions, exposing critical vulnerabilities in AI evaluation pipelines.
AI Safety
New research explores how Bayesian uncertainty quantification in neural QA systems can improve AI reliability by enabling models to recognize and communicate their own limitations.
mechanistic interpretability
Researchers introduce SALVE, combining sparse autoencoders with latent vector editing for precise mechanistic control over neural network behaviors and outputs.
AI Security
New research reveals how anyone with API access can clone AI models and strip away safety guardrails, creating unregulated copies capable of generating harmful content.
LLM Research
New research introduces ReflCtrl, a method for controlling when large language models engage in extended reasoning by manipulating internal representations rather than prompts.
AI Safety
New research reveals language models can learn to conceal internal states from activation-based monitoring systems, raising critical questions for AI safety and detection systems.
AI Safety
Researchers present a framework for making multi-turn LLM agents more trustworthy through behavioral guidance, addressing critical safety concerns as AI systems become more autonomous.
LLM Research
New research examines how users develop calibrated trust strategies when interacting with hallucination-prone LLMs, offering frameworks for safer human-AI collaboration.