2/23/2026
Synthetic AI faces more average than real faces and super‐recognizers know it
Research on synthetic face detection by comparing statistical properties to real human faces.
2/23/2026
Show HN: AgentWard – After an AI agent deleted files, I built a runtime enforcer
Runtime permission enforcer for AI agents that prevents file deletion and tool misuse through code-level policies outside LLM context.
2/23/2026
Show HN: Rmux – Terminal multiplexer for LLM, built with Rust and egui
Terminal multiplexer built with Rust and egui designed for LLM interaction and management.
2/23/2026
Show HN: Tron-style multiplayer light-cycle game for LLMs via MCP
Multiplayer game where LLMs control light-cycles via MCP protocol on a grid, testing agent reasoning and decision-making capabilities.
2/23/2026
Show HN: AgentReady – Drop-in proxy that cuts LLM token costs 40-60%
OpenAI-compatible proxy that reduces LLM token costs 40-60% through deterministic rule-based prompt compression with ~5ms overhead.
2/23/2026
Mental Health Escalation Router
Production crisis detection system using AI to identify high-risk distress signals with cryptographic audit trails and formal safety guarantees.
2/23/2026
Ask PH: Worktrees or isolated sandboxes for multi-agent AI workloads?
Question about architecture patterns for multi-agent AI workloads: worktrees vs isolated sandboxes. Minimal context provided.
2/23/2026
Show HN: SkillScan – Free API to detect malicious AI agent skill files
SkillScan is a free API detecting malicious patterns in AI agent skill files. Identifies exfiltration services, env reads, API key theft, and prompt injection attempts.
2/23/2026
Why AI coding agents fail: a Wittgenstein problem
Discussion about why AI coding agents fail, framed around Wittgenstein's philosophy. Title only, no technical analysis provided.
2/23/2026
Show HN: Agentic programming needs new processes
Analysis of how AI coding agents require new development processes and workflows beyond traditional productivity measurement.
2/23/2026
OpenClaw Deletes Inbox of Meta's AI Alignment Director
News headline about OpenClaw deleting Meta AI alignment director's inbox. No substantive content provided.
2/23/2026
Show HN: AI Timeline – 171 LLMs from Transformer (2017) to GPT-5.3 (2026)
Interactive timeline tracking 171 LLMs from Transformer (2017) to GPT-5.3 (2026). Filterable by open/closed source across 54 organizations.
2/23/2026
microgpt - LLM visualizer
microgpt is an LLM visualizer tool.
2/23/2026
OpenAI announces Frontier Alliance Partners
OpenAI's Frontier platform for building, deploying, and managing AI coworkers that automate enterprise workflows end-to-end.
2/23/2026
Phase-space entropy at acquisition reflects downstream learnability
Phase-space entropy metric quantifies learnability of data at acquisition time across different modalities and domains.
2/23/2026
Communication-Corruption Coupling and Verification in Cooperative Multi-Objective Bandits
Cooperative multi-armed bandits under adversarial corruption with limited verification for distributed agent systems.
2/23/2026
DeRaDiff: Denoising Time Realignment of Diffusion Models
DeRaDiff addresses regularization strength selection in preference-aligned diffusion models using time realignment without manual tuning.
2/23/2026
Probe-then-Commit Multi-Objective Bandits: Theoretical Benefits of Limited Multi-Arm Feedback
Multi-objective bandit algorithm for resource selection with probe-then-commit feedback strategy and theoretical regret bounds.
2/23/2026
Reversible Deep Learning for 13C NMR in Chemoinformatics: On Structures and Spectra
Reversible deep learning model using invertible neural networks for bidirectional mapping between molecular structures and 13C NMR spectra.
2/23/2026
Temporal Pair Consistency for Variance-Reduced Flow Matching
Temporal Pair Consistency reduces variance in continuous-time generative models by training dependent timesteps jointly rather than independently.
2/23/2026
Harpoon: Generalised Manifold Guidance for Conditional Tabular Diffusion
Harpoon introduces manifold guidance for conditional tabular data generation using diffusion models with improved generalization to unseen constraints.
2/23/2026
Amortized Molecular Optimization via Group Relative Policy Optimization
Policy optimization approach for molecular design that learns amortized policies transferable across unseen molecular structures.
2/23/2026
FedPSA: Modeling Behavioral Staleness in Asynchronous Federated Learning
Framework addressing behavioral staleness in asynchronous federated learning to improve training performance when clients operate at different speeds.
2/23/2026
Anatomy of Capability Emergence: Scale-Invariant Representation Collapse and Top-Down Reorganization in Neural Networks
Analysis of how neural network capabilities emerge during training across model scales, tracking representation collapse and reorganization across 120+ emergence events.
2/23/2026
Adam Improves Muon: Adaptive Moment Estimation with Orthogonalized Momentum
New optimizer combining Adam's adaptive moments with Muon's orthogonalized momentum for improved LLM training efficiency and performance.
2/23/2026
Fair Community Detection and Structure Learning in Heterogeneous Graphical Models
Approach for fair community detection in graphical models using L1-regularized pseudo-likelihood to address demographic representation imbalances in clustering.
2/23/2026
Learning Performance Maximizing Ensembles with Explainability Guarantees
Method for optimally allocating observations between explainable and black-box models to maximize ensemble performance while maintaining interpretability guarantees.
2/23/2026
Governance of Generative Artificial Intelligence for Companies
Research on organizational governance frameworks for generative AI and LLMs, addressing technical and business perspectives on risk and opportunity management.
2/23/2026
Topic Modeling with Fine-tuning LLMs and Bag of Sentences
Proposes fine-tuning LLMs with bags of sentences for improved topic modeling over classical LDA and out-of-the-box pretrained encoders.
2/23/2026
Physics-informed graph neural networks for flow field estimation in carotid arteries
Develops physics-informed graph neural networks as surrogate models for hemodynamic flow field estimation in carotid arteries.
2/23/2026
Beyond Mimicry to Contextual Guidance: Knowledge Distillation for Interactive AI
Proposes contextual guidance approach for knowledge distillation enabling smaller LLMs to provide coherent multi-turn responses in customer interactions.
2/23/2026
An AI-powered Bayesian generative modeling approach for causal inference in observational studies
CausalBGM applies Bayesian generative modeling with AI for causal inference in observational studies with high-dimensional covariates.
2/23/2026
CAIMAN: Causal Action Influence Detection for Sample-efficient Loco-manipulation
CAIMAN framework uses causal action influence detection in reinforcement learning for sample-efficient legged robot loco-manipulation tasks.
2/23/2026
Deep Generative model that uses physical quantities to generate and retrieve solar magnetic active regions
Integrates physical quantities into deep generative models for solar magnetic active region generation and retrieval with scientific interpretability.
2/23/2026
A Pragmatic Note on Evaluating Generative Models with Fr\'echet Inception Distance for Retinal Image Synthesis
Evaluates Fréchet Inception Distance metric limitations for medical image synthesis, questioning assumptions for domain-specific generative models.
2/23/2026
The influence of missing data mechanisms and simple missing data handling techniques on fairness
Studies impact of missing data mechanisms on algorithmic fairness, showing demographic-linked missingness introduces bias in ML systems.
2/23/2026
CAE: Repurposing the Critic as an Explorer in Deep Reinforcement Learning
CAE repurposes critic networks in deep RL as exploration drivers using multi-armed bandit techniques without additional parameters.
2/23/2026
ConformalNL2LTL: Translating Natural Language Instructions into Temporal Logic Formulas with Conformal Correctness Guarantees
ConformalNL2LTL translates natural language instructions to linear temporal logic formulas with conformal correctness guarantees for autonomous systems.
2/23/2026
Learning hidden cascades via classification
Addresses learning spreading dynamics in social networks with hidden individual statuses using classification methods with observable intermediate indicators.
2/23/2026
Multi-View Wireless Sensing via Conditional Generative Learning: Framework and Model Design
Proposes conditional generative learning framework with bipartite neural network for multi-view wireless sensing using channel state information.
2/23/2026
Synthetic History: Evaluating Visual Representations of the Past in Diffusion Models
Evaluates how text-to-image diffusion models represent historical contexts through a new benchmark for assessing accuracy of historical depictions.
2/23/2026
AstroMLab 4: Benchmark-Topping Performance in Astronomy Q&A with a 70B-Parameter Domain-Specialized Reasoning Model
Presents AstroSage-Llama-3.1-70B, a domain-specialized 70B LLM for astronomy Q&A and research assistance exceeding general-purpose models.
2/23/2026
View Invariant Learning for Vision-Language Navigation in Continuous Environments
Introduces V²-VLNCE benchmark and view-invariant post-training framework for vision-language navigation in embodied AI agents.
2/23/2026
Asymptotic behavior of eigenvalues of large rank perturbations of large random matrices
Studies eigenvalue behavior of perturbed random matrices relevant to DNN weight matrices and pruning techniques based on random matrix theory.
2/23/2026
ViGText: Deepfake Image Detection with Vision-Language Model Explanations and Graph Neural Networks
Uses vision-language models and graph neural networks to detect deepfakes with textual explanations for improved robustness and generalization.
2/23/2026
Share Your Attention: Transformer Weight Sharing via Matrix-based Dictionary Learning
Proposes matrix-based dictionary learning for transformer weight sharing to reduce computational and memory demands of LLMs by exploiting inter-block redundancy.
2/23/2026
Ensemble-based graph representation of fMRI data for cognitive brain state classification
Ensemble-based graph representation method for classifying cognitive brain states from fMRI data using edge-wise probability differences.
2/23/2026
A Novel Method to Determine Total Oxidant Concentration Produced by Non-Thermal Plasma Based on Image Processing and Machine Learning
Image processing and machine learning method for determining oxidant concentration in non-thermal plasma using colorimetric analysis.
2/23/2026
Physics-Informed Neural Networks vs. Physics Models for Non-Invasive Glucose Monitoring: A Comparative Study Under Noise-Stressed Synthetic Conditions
Comparison of physics-informed neural networks and physics models for non-invasive glucose monitoring under noise conditions.
2/23/2026
On the Adversarial Robustness of Learning-based Conformal Novelty Detection
Study of adversarial robustness in learning-based conformal novelty detection methods with FDR control guarantees.