127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “safety”

22,398 results

Safety

training to benchmarks ≠ getting to AGI

DGX agent

training to benchmarks ≠ getting to AGI This suggests that Opus 5 's gain on ARC-AGI-3 was the result of specific training to improve on that eval, and not a generalized increase in abstract reasoning

safetygary-marcus--x

26 Jul 2026

Safety

Search: “safety”

training to benchmarks ≠ getting to AGI

All anyone has to do is go back 15 years and look at all the ridiculous predictions Elmo has made about Mars, self driving cars, his ridicul…

I am surprised how few people are aware that the reasoning for OpenAI/Anthropic models is all encrypted. The 'reasoning' you see in the UI i…

The two giant generative AI startups were treated like gods for a couple years. Both are now facing massive pushback.

When a normal company does a bad thing, they take responsibility + apologize + outline how it won't happen again. OpenAI instead is like 'we…

A Framework for Reputation Aware Uninorm-driven Consensus Algorithms for Blockchain Networks

A Self-Evolving Default Action for Cooperative Tasks with Continuous Action Space

A Unified Moral-Value Dataset for Instruction Tuning

Adaptive Depth Sparse Framework: Similarity-Driven Resource Allocation for Pre-Trained LLMs

Anticipate Before Acting: Future-State-Conditioned Vision-Language Navigation

Approximate Quantum State Preparation Through Proximal Policy Optimization

ARCO: Adaptive Rubrics with Co-Evolution for Multi-Step LLM-Based Agents

ASTRA-Net: Anatomy-Specific Transfer and Representation Alignment for Drug-Induced Sleep Endoscopy Segmentation

AttriMem: Attribution-Guided Process Feedback for Agent Memory Learning

Axolotl3D: a Unified Framework for Faithful 3D Shape Completion

Belief Propagation in LLM World Models: Measuring Strategic Information Bias with Prediction Markets

Beyond Sycophancy: Structured Resistance and Compliance in LLM Moral Reasoning

Climate-resilient electric vehicle charging infrastructure for sustainable cities: An interpretable causal-ensemble framework for preventive maintenance and low-carbon mobility

Confidently Deceptive: How Confidence Amplifies the Risk of LLM Deception

CSPF: A Constrained Shared-Private Fusion Method for Non-Verifiable Preference Evaluation

DINOde: Continuous Vision-Text Alignment for Open-Vocabulary Semantic Segmentation

Distribution-Alignment Bridge for Uncertainty-Aware Text-to-Video Retrieval

DTIF: Robust Loop Closure Detection via Delaunay Triangle Topology in Complex Forests

DynaMark: A Reinforcement Learning Framework for Dynamic Watermarking in Industrial Machine Tool Controllers

EmoAgent-R1: Towards Multimodal Emotion Understanding with Reinforcement Learning-based Dynamic Agent Specialization

EmoSpace: Immersive Affective Image Generation Guided by Fine-Grained Emotion Prototypes

Enhancing Explainable Cardiac Diagnosis with Guide-Grounded Multimodal LLMs

Environment-Aware Channel Inference via Cross-Modal Flow: From Multimodal Sensing to Wireless Channels

Evaluating Risks in Weak-to-Strong Alignment: A Bias-Variance Perspective

EvoSQL: Memory-Augmented Critic-Generator Co-Evolution for Text-to-SQL

Expert Behavior Prior Reinforcement Learning

Explainability Framework for Policy-Aware Autonomous Agents

Explainable graph attention network for stress recognition (StressGAT) via differential action units

FELT: Generating Tactile Signals from Vision for Visuo-Tactile Manipulation

FORGE-plus: Force-Budgeted Recovery for Contact-Rich Assembly with a Frozen LLM Supervisor

From Agent Failures to Text Policies: What Works and What Breaks

From Static Bibliometrics to Dynamic Knowledge Graphs: An LLM-Powered Framework for Modernizing Science, Technology, and Innovation (STI) Analytics

Generative AI and Agency in Education: A Critical Scoping Review and Thematic Analysis

Generative Artificial Intelligence in Bioinformatics: A Systematic Review of Models, Applications, and Methodological Advances

GLAM-SLAM: Real-time Gaussian Large-scale Mapping via Flow Densification and Spatial Decomposition

GroupVideo: Multi-Identity Customized Text-to-Video Generation

GuidedAttention: Interpretable and Correctable Visual Attention for OOD-Robust Robot Manipulation via Imitation Learning

Inference-Time Scaling of Diffusion Models via Progressive Seed Pruning

KeySI: An Interaction Framework for Tuning Text Embeddings Based on Human Feedback

Let’s build seven trillion dollars worth of data centers for sports betting!

MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs

Multivariate Planar Curves: A Statistical Framework for Shape Analysis in Images

One Round Is All You Need: Analytic Federated Learning for Task-Heterogeneous Multi-Label Medical Image Classification