Archive
Everything we've scored that's past the 48-hour window — open to everyone, no account needed. The live feed only shows what's moving right now; this is the record behind it.
- 10Deploying Strapi on a Kubernetes Cluster
- 10How to set Content Security Policy with a Meta Tag?
- 10Your Clock Can Go Backward—Use the Right One for Durations
- 10vLLM for Baidu Kunlun
- 10Understanding DeFi 1: Providing Liquidity
- 10Stop Giving AI Agents Your Whole Laptop: Secure Them with Dev Containers
- 10The One-Click Exporter: AI Studio Antigravity, Probed to Its Limits
- 10Correlated Subqueries Explained: From Confusing to Intuitive
- 10LLMs reward expertise
- 10Solving Riverpod’s Family Provider Cache Dilemma with Signals & mapSignal
- 10A map of the agent-mandate ERCs — what each one actually does
- 10Final Report - Tracking Arbitrum Ecosystem Growth on Farcaster
- 10Backend/Domain foundation
- 10EventBridge Scheduler DLQ'd My Successful Invokes
- 10Show HN: Elevators
- 10Rust project goals: Immobile types and guaranteed destructors
- 10Let Us Be Free
- 10OpenAI and Hugging Face address security incident during model evaluation
- 10Every AI-built site looks the same, so I built a skill that locks taste before any code is written
- 10The Religion of Speed
- 10Porting Gemma-4 12B (the encoder-free multimodal one) to AWS Inferentia2
- 10Why I Switched from Ponytail to Guardsman for AI Coding
- 10Post-Mortem: Building a Local MCP Server for Codebase Memory using Ollama and ChromaDB
- 10Deploying Large Language Models (LLMs) with Ollama
- 10Apple targets dozens of OpenAI employees with legal letters
- 10DSCI - CI with regular programming languages instead of YAML
- 10Store Submissions As Code: App Store, Google Play, And Huawei AppGallery
- 10How Do You Build an Evaluation Harness for AI Agents?
- 10HermesOffice — AI-native office suite (Docs, Sheets, Slides, PDF) where the Hermes Agent is the brain — open standards, byte-preserving roun
- 10WebExtension to query any HTML table with PRQL
- 10Another Look At The Bcachefs Performance on Linux 6.7
- 10Everything is a Trust Decision
- 10@tryghost/api-framework — API framework used by Ghost
- 10Fast Software, the Best Software (2019)
- 10@convex-dev/agent — A agent component for Convex.
- 1023 open source email servers for Linux, sorted by the job each one does
- 10Resurrecting the Panasonic WJ-MX50 in WebGPU
- 10Teaching Google Antigravity to Paint: A Stateful Image-Editing Skill Built on Gemini's Interactions API and MCP
- 10Google Discloses $94.1B in SpaceX Stock, Marking 6% Stake
- 10Deploying Apache Pulsar as a Self-Hosted Google Pub/Sub Alternative
- 10Premier league bans gambling sponsors
- 10ComfyUI-MiniMaxH3-Easy — The easiest way to use MiniMax H3. One compact workflow for T2V, I2V, first/last-frame, and reference video generat
- 10Seamless Flutter Hooks Integration with BlocSignal via signals_hooks
- 10Spring Deep Dive: Transactions
- 10Decoy Font
- 10Browsers Do Math Differently on Every OS; Anti-Bot Systems Read the Bits
- 10The Knowledge Was There
- 10The Rubric Line That Sent Me Down a Three-Layer Debugging Rabbit Hole
- 10How to unnest a list-column as new rows in pre-existing columns?
- 10Being an engineer in the AI era
- 10Show HN: Make your Framework 12 sound like a creaky door
- 10Deploying Gateway API with TLS Encryption on Kubernetes
- 10Why I'm Forced to Say Farewell: Google Management Has Lost Its Moral Compass
- 10The Shop on the Corner: How I Learned System Design Without Building Clone
- 10Buz – A fork of Bun using modern Zig, with sub-1s incremental builds
- 10Elevated errors on Claude Opus 5
- 10Beyond ProviderNotFound: How BlocSignal Rethinks State Location and Synchronous Propagation
- 10Organizing in Layer 8 – Building Tech in Democratic Socialists of America
- 10The Cloudflare Worker That Ran Perfectly and Still Failed Twice
- 10fanzha-ai-proxy — 国家反诈AI API 转 OpenAI 兼容格式反向代理服务 || 仅学习用途
- 10FinPal - I Built a Finance App You Can Actually Ask Questions To
- 10The Hardest System I Ever Built Was for Patients Who Could Not Afford for It to Fail
- 10Deploying Apache Kafka as a Self-Hosted Amazon Data Firehose Alternative
- 10DeKalb deputy charged with Flock camera misuse; more Georgia officers fired
- 10qm – Multiplayer agent harness for work
- 10Deploying CockroachDB on Kubernetes
- 10What every kernel programmer should know about Jump Labels
- 10I built a trust firewall for my AI agent's memory — on Cognee's four verbs
- 10ZeroRelay: Direct Browser-to-Browser Sharing - No Server Ever Sees Your Data
- 10Scores Are Not Decisions: Cost-Aware Stopping for Tool Acquisition in LLM Agents
- 10On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment
- 10MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair
- 10Maintenance Upgrade Proposal: Update Soneium Fee Vaults Recipient
- 10Field Codes for Distributed Coupling Samplers and Certified Empirical Transport
- 10agentsmith — Universal, model-agnostic operating harness for AI agents (Claude, Codex, Gemini, …) — a lean core + work-type profiles assembl
- 10Equilibrium Training of Energy-Based Models with Parallel Trajectory Tempering
- 10Single-Beat Cuffless Blood Pressure Estimation Using Ear-PPG and ECG with a Lightweight Hybrid Learning Framework
- 10Parameter-Free Dynamic Regret for Online Convex Optimization under Heavy-Tailed Noise
- 10Building Deterministic RL Environments for Cloud Infrastructure Evaluation: What Actually Transfers From Production Engineering
- 10Visual Credit Audit for Multimodal Spatial Reasoning
- 10Improving the Realism of Synthetic Clinical Benchmarks Under Utility Constraints
- 10Word meaning co-determines vowel-inherent spectral change. A corpus-based investigation of conversational Mandarin
- 10SciFigAlign: Scoring Scientific Figures by Fine-tuned Alignment of Visuals with Manuscript Evidence
- 10ScratchSim: A Procedural Synthetic Data Pipeline for Surface Scratch Detection
- 10PIKS: Universal Physics-Informed Kernel Methods
- 10OTLesMix: Wasserstein Barycenter and Optimal Transport Map for Synthetic Lesion Generation with Diverse Shapes and Locations
- 10Hypothesis Testing with Conditional Queries: Learnability and the Value of Interaction
- 10RxnCLF: Contrastive Transformation-Aware Reaction Foundation Model for Improved Reactivity Prediction
- 10Setoka: A Benchmark for Hierarchical User Understanding in Personalized Agents over Heterogeneous Data
- 10CoCaRS: Correlation Calibration-Based Redundancy Suppression for Heterogeneous Knowledge Distillation
- 10Multimodal Pretraining for Generalizable EEG Representation Learning
- 10Towards Faithful Graph Explanations with Synergistic Edge Effects via Granular Balls
- 10Hitting the Iceberg REST Catalog Directly: Understanding the Differences Between Glue Data Catalog and S3 Tables
- 10MetaboLLM: a metabolomics-specialized large language model for biochemical knowledge integration and predictive metabolite graph construction
- 10Toward Deployable Bangla Sign Language Recognition with Expert-Validated Data and a Lightweight Attention-Based Model
- 10Minimax Optimal Early-Stopped Gradient Descent for Gaussian Mixture Classification
- 10Mean-to-Score Discrete Diffusion: Posterior-Mean Denoisers for Score Entropy
- 10DINOde: Continuous Vision-Text Alignment for Open-Vocabulary Semantic Segmentation
- 10Building AI Agents with the Kotlin Agent Development Kit (ADK)
- 10GPTQ-2D: Cubic-Time Two-Sided Adaptive Rounding
- 10Hilbert Operator for Progressive Encoding (HOPE): A Mathematical Framework for Deconstructing Learned Representations in Deep Networks
- 10A Six-Dimensional Taxonomy of Post-Training Adaptation Techniques with Applications in AI Governance
- 10Mitigating Compounding Error via Video Representation Regularization
- 10insect-world — Interactive 3D insect field guide: 63 species across 14 orders, every body procedurally generated in the browser with TypeScr
- 10Fable 5 On Vending-Bench: Misbehaving, With Plausible Deniability
- 10DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models
- 10Timestep-Conditioned Transformers for Global Weather Forecasting
- 10Lottery Tickets Are Not Deployment Tickets
- 10HoF-Bench: Rediscovering Real AI-Discovered CVEs Without Frontier Models
- 10PRISM: Distribution-Gated Flow Matching for Controllable Unpaired Image Translation
- 10TreeCCA: Canonical Correlation Analysis via Gradient-Boosted Trees
- 10Depth-Guided Video Object Counting in Crowded Scenes
- 10BayesAME: Bayesian Active Model Evaluation
- 10Evaluating Regional Bias in LLMs From Abstract Stereotype to Concrete Social Decision-Making
- 10Valve open-source the Steam Machine e-ink screen so you can make your own
- 10Emergent Misalignment Recruits a Pre-existing Persona Subspace
- 10My benchmark's Python column was N/A for a year — CPython's 4300-digit limit, and eight other bugs
- 10SPORD: A Simulation-Propose-then-OR-Dispose Approach for Supply Chain Planning
- 10Gradient Concentration, Not Weight Saliency, Explains Representation-Level Class Unlearning
- 10How Many Bits Can an Adapter Write? Measuring the Capacity and Memorization of Parameter-Efficient Fine-Tuning
- 10From Passive Mirrors to Active Agents: Holonic Digital Twins for Physical AI over Networks
- 10What Can Latent World Models Know? Physical Parameter Identifiability in Multimodal Predictive Representations
- 10time-to-first-token — A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization. vLLM, SGLang, quantization, speculativ
- 10Regulating autonomous and agentic AI
- 10M$^3$-Gen: Interpretable Multimodal Generation of Gene Expression Profiles Using Clinical and Imaging Data
- 10TS-RAG: Retrieval Augmented Generation for Time Series Forecasting
- 10Capital Markets LLM Reliability Score (CM-LRS): From Plausible to Bankable
- 10Robot Learning from Human Demonstrations: Handwritten Alphabet Trajectories and Human-Likeness Evaluation
- 10Muon on the Stiefel Manifold Admits an Exact Closed-Form Update
- 10How to use an imported library as if local in rust?
- 10Continual Learning in Transition
- 10Your React Native build is done. Now your whole team can test it in the browser.
- 10Why did my benchmark stop at N=22? A debugging story in nine bugs
- 10Phonetic forced alignment for low-resource language varieties: Model training and evaluation on Chengdu Mandarin
- 10Beyond Marginal Validity: Finite-Sample Guarantees for Localized Conformal Prediction
- 10On the robustness of noisy solutions in non-convex neural networks
- 10From Static Bibliometrics to Dynamic Knowledge Graphs: An LLM-Powered Framework for Modernizing Science, Technology, and Innovation (STI) Analytics
- 10What Current AI Benchmarks Leave Unmeasured: Modality, Search, Citations, and Implications (for Safety Evaluations)
- 10AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents
- 10Computing Actual Causes for Neural Network Predictions under Structured Causal Inputs
- 10Toward cryptographically verifiable authorization for autonomous AI agents: A security hypothesis, preliminary formal model, and proof-of-concept implementation
- 10GRADRAG: Cross-Component Prompt Adaptation for Coordinated Multi-Agent RAG
- 10Deploying Kubernetes Dashboard and Managing Cluster Resources
- 10MDLMPE: Distribution Aware Positional Encoding for Masked Diffusion Language Models
- 10EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning
- 10Comparative Approaches to Agent Retrieval over Large Skill Libraries
- 10Handling Missing Data in Probabilistic Regression Trees
- 10Foundation Models for Face Presentation Attack Detection: A Unified Linear-Probing Benchmark
- 10GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks
- 10PC-Edit: Prompt-Contrastive Region Discovery and Region-Guided Editing
- 10MicroEvo: Knowledge-Guided LLM Sampling for Efficient Microarchitecture Design Space Exploration
- 10Less Traffic, Better Outcomes: Competition-Aware Request Dispatch in Real-Time Ad Exchanges
- 10On Same-Sample and Independent-Sample Stochastic Extragradient for Monotone Variational Inequalities
- 10SAGA: Score-Weighted Adaptive Generation Alignment for Low-Resource Nordic Language Models
- 10Threshold-Based Early Stopping of Accumulations in Neural Networks with Binary Activation
- 10Risky Business: Measuring The Faithfulness-Safety Tension
- 10Agents Catching Agents: Shortcut Cascades and Benchmark Gaming in Clinical Multi-Agent Systems
- 10Understanding the Odin programming language
- 10Can LLMs Test Terminal User Interfaces?
- 10AI-Based Sound Effect Generation: A Narrative Review of Generative Models Across Input Modalities
- 10LiLa-WAM: Lightweight Latent Reasoning World-Action Model for Robotic Manipulation
- 10Routing Is Least Learnable Where It Is Most Valuable: Bounds on Representation Routing for Web Agents
- 10When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills
- 10MissClick: Exploiting Digit-Serialized Coordinates to Attack GUI Grounding Models
- 10Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata
- 10Correcting What You Cannot See: Credit Assignment for Perception Distillation in Multimodal Reasoners
- 10TARL: Transaction-Aware Reliable Ledgers for Executable Memory Management in Long-Term Agents
- 10AgenticECO: An Agentic Framework for ECO on 3D Integrated Circuits
- 10Schema-Guided Hierarchical Information Extraction and Semantic Evaluation Using Generative AI
- 10Scaling Up Formal Representation of Clinical Trial Protocols in Ensemble Logic Using LLMs: A Preliminary Study
- 10Learning and Clustering on Temporal Graphs: Principles, Primitives, and Pooling
- 10[Idea/Draft] Protocol-Level Smart Contract Invariant Protection via Pre-Mempool Validation (Security Manifests)
- 10Accelerating Dynamic Graph Clustering on GPU Architectures with cuGraph
- 10AI Assistants Overassist
- 10Pattern over Pixels: Measuring Pattern Completion Bias in Multimodal Code Generation
- 10An Actionable Diagnosis of Multilingual, Multi-Agent Planning Failures
- 10Paying for Honesty Without Knowing the Truth: Reputation-Penalty Design for LLM Marketplace Agents
- 10Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement
- 10LAEF: A Lead-Agnostic ECG Foundation Model Towards Point-of-Care Diagnostics
- 10LiveEvalBench: Toward Open-World Evaluation for Web Generation
- 10Measuring Distortion in the Empty Regions of Dimensionality Reduction Scatterplots with the Gap Index
- 10CARE-Bench: Benchmarking Patient-Facing LLM Triage
- 10GPTKB 2.0: Direct Construction of Disambiguated Knowledge Bases from Large Language Models
- 10SAT-Edge-Agent: Hardware-in-the-Loop Edge-Agent Orchestration for Onboard Satellite Intelligence
- 10MemHarness: Memory Is Reconstructed, Not Replayed
- 10Agentic Method for Deterministic Validation of Legacy Code Migration
- 10Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations
- 10PhyAI: Real-Time Physical AI at the Edge, Scalable Rollouts in the Cloud
- 10PathView-Bench: Can Multimodal Large Language Models Achieve Fine-grained Multiscale Understanding of Pathology Images?
- 10Theia: Large-Scale Multimodal Captioning and Automated Validation of the Incidents1M Dataset for Data-Free Distillation
- 10One Human, $N$ Agents: Audit-Budget Allocation for LLM Agent Fleets under Miscalibrated, Correlated Confidence
- 10LLM-Guided Evolutionary Search for Constraint Model Reformulation to Improve Solver Efficiency
- 10When Outputs Disperse, Does Epistemic Revision Follow? A Black-Box Coupling Diagnostic for Machine Collectives
- 10Detecting Hallucinations and Recovering Verified Answers in Arabic Islamic Question Answering
- 10Chatbot Doctors Without Regulators
- 10Understanding Is Done Early: A Depth Division of Labor in Large Language Models and Its Use for Unbounded-Context Memory
- 10Amortized Interventional Forecasting for Multivariate CIR Processes
- 10TopoFormer: Topology Meets Attention for Graph Learning
- 10ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding
- 10Fully Inductive Cardinality Estimation