2/24/2026
Agents of Chaos: Breaches of trust in autonomous LLM agents
ArXiv paper on security/trust issues in autonomous LLM agents (abstract only, content truncated).
2/24/2026
Agents are not thinking, they are searching
Essay de-anthropomorphizing AI agents, framing them as search/utility tools rather than thinking entities.
2/24/2026
Show HN: VVMList – Vulnerable VMs organized by attack techniques
Cybersecurity resource organizing vulnerable VMs by attack techniques for CTF learners.
2/24/2026
Show HN: AegisMind Discover – cross-domain hypothesis generation from papers
System that reads research papers across domains to generate cross-domain hypotheses. Early stage with three discoveries published.
2/24/2026
HPC-AI explains embodied AI
Overview of embodied AI systems that perceive, adapt, and act in physical environments beyond code-based systems.
2/24/2026
The "AI Existential Risk" Industrial Complex
Opinion piece critical of AI existential risk advocacy and doomerism narratives.
2/24/2026
How can we compare local LLMs vs. APIs vs. subscriptions objectively?
Discussion comparing local LLMs versus API-based and subscription models. Addresses whether local models can match frontier-quality AI.
2/24/2026
Ask HN: Agentic search vs. RAG – what's your production experience?
Production experience thread comparing agentic search versus RAG. Community shares transition triggers, breakages, and hybrid approaches.
2/24/2026
Ask HN: Agentic search vs. RAG – what's your production experience?
Production experience thread comparing agentic search versus RAG. Community shares transition triggers, breakages, and hybrid approaches.
2/24/2026
Next-Markdown-mirror – make Next.js pages readable to AI (Markdown and llms.txt)
Next.js middleware serving clean Markdown instead of HTML to AI agents, reducing token waste from boilerplate by 2-5x for better LLM performance.
2/24/2026
Pi Coding Agent
Pi: minimal terminal coding agent with TypeScript extensions, npm packages, and multiple modes (interactive, RPC, SDK, JSON output).
2/24/2026
Show HN: I built iOS app to turn saved workout videos into structured routines
iOS app using video analysis to convert workout footage into structured fitness routines for users 35-55.
2/24/2026
Help me with positioning/marketing of my AI agent
Landing page for AI agent product that automates email, meetings, and task management with positioning for founders and managers.
2/24/2026
Show HN: A Claude Code hook that sends you to bed
Claude Code hook that reminds users to sleep during bedtime by injecting context reminders and logging violations. Open source tool.
2/24/2026
Claude Code to Figma: The Complete Guide to AI Driven Product Design Workflows
Guide on using Claude Code with Figma for AI-driven product design workflows, converting AI-generated code to editable design files.
2/24/2026
Show HN: Pragmatica Aether – a distributed Java runtime that replaces Kubernetes
Pragmatica Aether is distributed Java runtime for JVM applications with clustering and auto-scaling, alternative to Kubernetes. Open source.
2/24/2026
Show HN: Scheme-langserver – Digest incomplete code with static analysis
Scheme-langserver provides language server protocol support for Scheme/Lisp with goto-definition, auto-completion, and type inference.
2/24/2026
Everyone in AI is building the wrong thing for the same reason
Opinion piece on AI founders being caught in building momentum despite doubts about industry direction and priorities.
2/24/2026
Trolley: Run Terminal Apps Anywhere
Trolley bundles TUI executables with terminal emulator runtime for distribution to non-technical users on Linux/macOS. Pre-alpha stage.
2/24/2026
PCA-VAE: Differentiable Subspace Quantization without Codebook Collapse
PCA-VAE replaces vector quantization with differentiable online PCA bottleneck via Oja's rule, eliminating codebook collapse and straight-through estimators.
2/24/2026
TRUE: A Trustworthy Unified Explanation Framework for Large Language Model Reasoning
Trustworthy Unified Explanation framework for interpreting LLM reasoning, revealing stability and systematic failure mechanisms across instances.
2/24/2026
DeepInterestGR: Mining Deep Multi-Interest Using Multi-Modal LLMs for Generative Recommendation
Generative recommendation framework using multi-modal LLMs to mine deep multi-interests beyond shallow behavioral signals for semantic ID prediction.
2/24/2026
From Human-Level AI Tales to AI Leveling Human Scales
Framework for calibrating AI benchmark performance against world population baselines to provide human-anchored capability scales.
2/24/2026
LoMime: Query-Efficient Membership Inference using Model Extraction in Label-Only Settings
Membership inference attacks on ML models using model extraction in label-only settings without access to confidence scores or shadow models.
2/24/2026
Exponential Convergence of (Stochastic) Gradient Descent for Separable Logistic Regression
Theoretical analysis of gradient descent convergence rates for separable logistic regression under large step sizes and unstable regimes.
2/24/2026
Conditionally Site-Independent Neural Evolution of Antibody Sequences
Deep learning method for antibody sequence engineering using phylogenetic models to capture evolutionary dynamics in affinity maturation.
2/24/2026
Why ReLU? A Bit-Model Dichotomy for Deep Network Training
Theoretical analysis of neural network training complexity under Real-RAM vs bit-model computation, proving ERM for simple networks is ∃ℝ-complete.
2/24/2026
Learning to Detect Language Model Training Data via Active Reconstruction
Proposes Active Data Reconstruction Attack (ADRA) for detecting LLM training data through active model manipulation rather than passive membership inference.
2/24/2026
Pushing the Limits of Inverse Lithography with Generative Reinforcement Learning
Applies generative RL to inverse lithography for semiconductor manufacturing mask synthesis, replacing deterministic approaches with conditional sampling.
2/24/2026
A Markovian View of Iterative-Feedback Loops in Image Generative Models: Neural Resonance and Model Collapse
Analyzes model collapse in image generative models through iterative feedback loops using Markovian framework, revealing neural resonance phenomena in latent space.
2/24/2026
Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-Tuning
Addresses intransitive preferences in LLM fine-tuning via preference learning, proposing methods to handle cyclic preference conflicts in multi-objective optimization.
2/24/2026
IDLM: Inverse-distilled Diffusion Language Models
Inverse distillation for diffusion language models. Accelerates discrete diffusion models for faster text generation inference.
2/24/2026
RKHS Representation of Algebraic Convolutional Filters with Integral Operators
RKHS representation theory for algebraic convolutional filters using integral operators. Signal processing framework for continuous models.
2/24/2026
The Power of Decaying Steps: Enhancing Attack Stability and Transferability for Sign-based Optimizers
Analysis of sign-based optimizers for adversarial attacks. Studies attack stability and transferability using decaying step sizes.
2/24/2026
Learning from Complexity: Exploring Dynamic Sample Pruning of Spatio-Temporal Training
Dynamic sample pruning for spatio-temporal forecasting. Optimizes training data efficiency for deep learning on large datasets.
2/24/2026
Robust Predictive Uncertainty and Double Descent in Contaminated Bayesian Random Features
Robust Bayesian random feature regression with contaminated priors. Studies double descent phenomenon under model misspecification.
2/24/2026
Detecting labeling bias using influence functions
Influence functions for detecting labeling bias in datasets. Addresses fairness issues from biased data collection.
2/24/2026
Test-Time Learning of Causal Structure from Interventional Data
Test-time learning method for causal structure discovery from interventional data. Combines test-time training with causal inference.
2/24/2026
Celo2: Towards Learned Optimization Free Lunch
Celo2 learned optimizer with improved meta-generalization. Aims for practical adoption of learned optimization rules beyond hand-designed optimizers.
2/24/2026
Incremental Learning of Sparse Attention Patterns in Transformers
Analysis of how transformers learn sparse attention patterns incrementally. Studies information integration from multiple past positions.
2/24/2026
Virtual Parameter Sharpening: Dynamic Low-Rank Perturbations for Inference-Time Reasoning Enhancement
Virtual Parameter Sharpening for inference-time reasoning enhancement. Dynamic low-rank perturbations for transformer adaptation without persistent parameters.
2/24/2026
Online Realizable Regression and Applications for ReLU Networks
Theoretical analysis of realizable online regression under metric-like losses. Studies ReLU networks in adversarial setting.
2/24/2026
Adaptive Problem Generation via Symbolic Representations
Adaptive problem generation via symbolic representations for training small open-weight LMs on math tasks. Data generation using RL with verifiable rewards.
2/24/2026
HybridFL: A Federated Learning Approach for Financial Crime Detection
Federated learning approach for financial crime detection handling hybrid data distributions. Privacy-preserving collaborative ML.
2/24/2026
How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization
Dynamic rollout allocation and policy optimization for LLM reasoning with verifiable rewards. Improves RL training efficiency for reasoning tasks.
2/24/2026
Understanding Empirical Unlearning with Combinatorial Interpretability
Combinatorial interpretability framework for understanding knowledge persistence in unlearning. Studies how information is retained in foundation models.
2/24/2026
Evaluating SAP RPT-1 for Enterprise Business Process Prediction: In-Context Learning vs. Traditional Machine Learning on Structured SAP Data
Evaluation of SAP's RPT-1 tabular foundation model on enterprise data. Compares in-context learning vs traditional ML on structured datasets.
2/24/2026
Alternating Bi-Objective Optimization for Explainable Neuro-Fuzzy Systems
Gradient-based optimization for explainable neuro-fuzzy systems. Addresses accuracy-explainability tradeoff in fuzzy AI models.
2/24/2026
DGPO: RL-Steered Graph Diffusion for Neural Architecture Generation
RL-steered graph diffusion for neural architecture search. Uses reinforcement learning to guide generative models for DAG-based NAS.
2/24/2026
Spectral bias in physics-informed and operator learning: Analysis and mitigation guidelines
Research on spectral bias in physics-informed neural networks and KANs for solving PDEs. Analysis of learning dynamics and mitigation strategies.