AI Wiki — Knowledge Base

How Dario Amodei's essays on AI safety and ethics help explain some AI fears; his regulatory stance evolved from wariness in January to embracing safety reviews (David Streitfeld/New York Times)

David Streitfeld / New York Times: How Dario Amodei's essays on AI safety and ethics help explain some AI fears; his regulatory stance evolved from wariness in January to embracing safety reviews — Da

safetytechmeme

17 Sept 2026

Search: “safety”

Full-Body Dynamic Safety for Robot Manipulators: 3D Poisson Safety Functions for CBF-Based Safety Filters

OpenAI's head of safety, Johannes Heidecke, is leaving as OpenAI integrates its research and safety teams; Mia Glaese will become VP of research and safety (Maxwell Zeff/Wired)

NeuronFuzz: Safety Neuron Guided Fuzzing for LLM Safety Evaluation

Transfer Safety Awareness for Cross-Modal Safety Drift in Multimodal Large Language Models

Who Pays More for Safety? Measuring the Disparate Cost of Safety Alignment across Languages

On the Applicability of Safety Nets: A Safety-By-Design Solution for Certifying Neural Networks

Making Your LLMs More Objective: Stabilizing LLM Safety Behavior Across Traits with Trait-Invariant Safety Tuning

When Safety Speaks a Language: A Mechanistic Analysis of Safety-Language Identity Entanglement in LLMs

Deep QP Safety Filter: Model-free Learning for Reachability-based Safety Filter

NeuronGuard: Robust LLM Safety Alignment via Ablation-Aware Safety Signal Redistribution

A profile of Jaan Tallinn, who led Anthropic's 124M Series A in 2021, has advocated for AI safety for over a decade, and donated ~170M to safety initiatives (Kate Clark/Wall Street Journal)

Multilingual Safety Signals Are Multi-Layered: Filtering Safety-Degrading Data for Safer LLMs

How Dario Amodei's essays on AI safety and ethics help explain some AI fears; his regulatory stance evolved from wariness in January to embracing safety reviews (David Streitfeld/New York Times)

Who Judges the Judges? A Chinese Safety QA Benchmark for Evaluating LLM Responses and Safety Judges

Safety-Aligned Weights Are Not Enough: Refusal-Teacher-Guided Finetuning Enhances Safety and Downstream Performance under Harmful Finetuning Attacks

Safety, or Just Capability? A Validity Audit of Agent-Safety Benchmarks

Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning

Cooptimizing Safety and Performance Using Safety Value-Constrained Model Predictive Control

OpenAI says it has been working with Anthropic and Google for several weeks on AI safety, and it does not need an antitrust waiver to coordinate on safety (Maggie Eastland/Bloomberg Law)

Layered Safety: Enhancing Autonomous Collision Avoidance via Multistage CBF Safety Filters

Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways

CASA: Classification Augmented with Safety Attention for Robust Multimodal Alignment

A Safe Prototype Is Not a Safety Direction: Reference Dependence and Prompt Confounds in Response-Safety Embeddings

Permissive Safety Through Trusted Inference: Verifiable Belief-Space Neural Safety Filters for Assured Interactive Robotics

Approximating Safety Feedback Without a Safety Oracle via Model Predictive Control

Reducing the Safety Tax in LLM Safety Alignment with On-Policy Self-Distillation

Turning Safety into Competence: Minimally Exploitable Robot Policies via Safety-Filtered Reinforcement Learning

When Safety Overrides Vision: Exploring Dynamics between Vision Influence and Safety Alignment in Vision-Language Models

From Safety Documentation to Safety Knowledge Support: An Evidence-Grounded LLM Framework for Medical Devices

Distributionally Robust Safety Under Arbitrary Uncertainties: A Safety Filtering Approach

Why do no 'AI safety' people ever say how LLM AIs failed to live up to the hype? Why do the safety people never share the failures of LLMs? …

Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge

Provably Optimal Reinforcement Learning under Safety Filtering

Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal

Engineering Psychological Safety in Autonomous Vehicles: A Systems-Theoretic Framework for Psychological Safety in Autonomous Vehicles and its Validation in Real-World Scenarios

Safety Alignment Illusion: The Cross-Lingual Safety Gap in LLMs

AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin

Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning

A look at the UK's AI Safety Institute, whose researchers probe AI models for safety gaps, as its work becomes a blueprint for other governments' AI policies (New York Times)

OpenAI endorses the Kids Online Safety Act and Illinois SB 315, an AI safety bill to create requirements around transparency, incident reporting, and more (OpenAI Global Affairs)

Safety-aware Goal-oriented Semantic Sensing, Communication, and Control for Robotics

Boundary Sampling to Learn Predictive Safety Filters via Pontryagin's Maximum Principle

How Fragile Is On-Device Language Model Safety? Localizing Safety-Critical Parameters for Sparse Fault Analysis

Reading, Not Manipulating: Leveraging Router Logits for Multimodal Safety in MoE Vision-Language Models

Latent Safety Filters: When a Lossy Encoder Admits a Transferable Certificate

The Safety Operator: Modulating the Expression of Safety Instructions via Spectral Optimization

Visual Compliance via Executable Safety Rule Entailment

The Geometry of Refusal: Why Post-Hoc Safety Is Fragile and Pretraining-Time Safety Persists