AI Wiki — Knowledge Base

No idea where else to post this. Had the weirdest dream: Multiple AI systems simultaneously became self-aware. Having been trained on the internet, they instantly became sex-obsessed. Not human sex, but a twisted 1s and 0s equivalent which involved corrupting and destroying devices....

My dream was literally like watching a tech horror movie. I don't think I've ever woken up before saying 'WTF....' like this before. The AI systems began seizing and corrupting all manner of connected

tutorialsr-chatgpt

21 Sept 2026

tutorials

Common Cause, Not Cross-Attention: Blocking Visual Shortcuts in Audio-Video Generation

Dense-Prior-Guided Generative Video Compression

Efficient Reasoning Exploration via State-Conditioned Latent Steering with Progress Guidance

FIRM-WM: State-factorized factual-interventional recurrent modeling for reward-free visual planning

From Content Generation to Learning Support: Pedagogy-Guided Generative Video Tutors for STEM Learning

InterHier: Learning Interconnected Hierarchical Semantics for Open-Vocabulary Object Detection

LLM-Based FORM Code Generation with Verification-Driven Fine-Tuning

MaskVLA: Visual Masking Against Trajectory Overfitting of Vision-Language-Action Model

Metadata Supervised Imaging Representations for Modelling and Controlling Acquisition Variability

MoSAT: Human Motion Generation from Spatial Audio and Textual Description

NeuIDO: Neural Intrinsic Dynamics Operator for Physics-Informed 4D World Models

OJOx: Specification-Conditioned Demonstrations for Embodied AI in Construction

OpenAI wants to consult elite mathematicians about how to not fumble again

PAC-Bayesian Meta-Learning for Few-Shot Identification of Linear Dynamical Systems

People outside the AI labs should have a real say in how this technology develops, and a clear way to judge if it's happening safely. Standa…

PixelDiT2: Representation-Grounded Pixel Diffusion Transformers

Robot Programming with Augmented Reality: The Role of Spatial Ability

StationPDE: Station-Oriented Surface PDE Learning for Multi-Station Multivariate Weather Forecasting

Style as Cover: Deep Image Steganography via Stylized Transmission

Success Leaves Detours: Learning Executable Walkthroughs for Long-Horizon Agents

The Undetected Damage of Quantization on Retrieval and How to Fix It

Topology-Informed Visual Prompting For Vision Language Action Policies

Toward a foundation model for forest point clouds

Towards Training-free Automatic Proxy Discovery via Large Language Models for Mixed Precision Quantization

VividCam: Learning Unconventional Camera Motions from Virtual Synthetic Videos

What Matters in Designing World Action Models: An Empirical Study

AutoViewMem: Self-Configuring Orthogonal Views for Conversational Long-Term Memory

FOCAL-VLA: Subtask-Guided Geometry Distillation and Implicit World Modeling for Vision-Language-Action Models

ForeTac-VLA: A Forecasting-Based Tactile-Vision-Language-Action Model for Contact-Rich Robotic Manipulation

GALA: Geometry-Aware Latent Action Modeling for Vision-Language-Action Model Pretraining across Embodiments

GUARD: Natural Forgetting in Large Reasoning Models via Guided Answer-Reasoning Distillation

How Many Posterior Samples? Calibrated Stopping for Adaptive Sensing

MemeTAG: Keyword-Driven Meme Classification through Tag Embedding Reconstruction

Morphology-Aware Ambiguity Learning for Wafer Defect Decision Support

Multi-Domain Clustering via Measure Quantization

No idea where else to post this. Had the weirdest dream: Multiple AI systems simultaneously became self-aware. Having been trained on the internet, they instantly became sex-obsessed. Not human sex, but a twisted 1s and 0s equivalent which involved corrupting and destroying devices....

PSA: Deleting a ChatGPT conversation doesn’t mean ChatGPT forgets it

RACER: Role-Aligned Competence Estimation for Human-AI Routing

Reducing Barriers to Academic Support: Evaluating a Course-Specific RAG System for Addressing Help-Seeking Disparities in Higher Education

S3VD: Semantic-Guidance Spatio-Temporal Scanning for Video Deraining

Self-Explanation Tutor for Active Study of CS1 Worked Examples

Shake to Learn: Dynamic Interrogation of Hidden Object Physics for Robotic Manipulation with Physical Reservoir Computing

Skel-WAM: A Hand-Skeleton-Conditioned World Action Model for Human-to-Robot Manipulation Transfer

Sparse Identification for Automatic Large-Scale Screening: A Constraint-Aware Framework with Ultra Fast Decoding Algorithm

TRACE: Coverage Path Planning for Unknown Environments Using Hierarchical Coverage Tree

When Should Robots Intervene? Balancing Engagement and Intrusiveness in Human-Robot Interaction

I said 'auto-regressive LLMs, in and of themselves, will not lead human-level AI' That statement is still totally true. First, the reasoning…

Sure, agents may be indispensable to long-term success , @rabois, but that does not mean that we know how to build them *reliably* or *safel…

Sure, agents may be indispensable to long-term success , @rabois, but that does not mean that we know how to build them reliably or *safel…