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.

• 65How to mask PII before using AI chat at work
• 63Why AI Agents Need a Real Browser Layer, Not Just Playwright Scripts
• 61@anthropic-ai/claude-agent-sdk-linux-x64 — Native CLI binary for @anthropic-ai/claude-agent-sdk on linux-x64
• 59TypeScript Generics: The Complete Guide (with Cheat Sheet)
• 59My Thoughts on the Bun Rust Rewrite
• 59What was your win this week??
• 58Zig Creator Calls Spade a Spade, Anthropic Blows Smoke
• 57Swift Classes — Everything You Knew About Structs Just Got More Complicated
• 57Looking for Stoplight Alternatives? 10 API Tools Developers Should Know in 2026
• 57A Pragmatic Look at AI in 2030
• 57Você recebeu acesso ao projeto. E agora?
• 57Bandit PCA with Minimax Optimal Regret
• 56Fast Whole-Brain, Geometry-Aware Functional Alignment for Cross-Subject Decoding
• 56The Singularity Space: A Generative Diffusion Framework for Signal Representation
• 56The Spectral Structure of Latent Treatment Effects
• 55Infrared Organization and Critical Cognitive Field Formation in Transformer Dynamics
• 55Learning Linear Temporal Specifications from Demonstrations with Uncertainty
• 55Normative Alignment of Recommender Systems via Internal Label Shift
• 55@ai-sdk/openai — The **[OpenAI provider](https://ai-sdk.dev/providers/ai-sdk-providers/openai)** for the [AI SDK](https://ai-sdk.dev/docs) c
• 55The Nuts and Bolts of Natural Language to SQL Translation: A Systematic Analysis of Model Pipeline Optimisation Approaches and their Interactions
• 54ZoRRO: A Zero-Weight Personalized Recommender System for Scalable News Recommendation
• 54Incremental Transformer for Surrogate-Based Inverse Design of Geopolymer Mixtures
• 53SETA: Scaling Environments for Terminal Agents
• 53Transferable Implicit Solvent Machine Learning Potential for Drugs and Proteins Approaching Ab Initio Accuracy
• 53next — The React Framework
• 53🤗 The Hugging Face Breach of 2026: When an AI Agent Hacked an AI Company
• 53Rewriting Bun in Rust
• 53Introducing Angular support for CopilotKit: bring any Agent into your app
• 53I built a collection of open-source Eve agents for AI based on the Vercel framework
• 53First-Order Modal Logic in HOL: Deep and Shallow Embeddings with Automated Faithfulness (Extended Preprint)
• 52I Regret Migrating to Codeberg
• 52LOGOS: A Living Logic for AI Agent Teams That Evolve With Humans
• 52Toward Contemplative LLM: A Modular Framework for Evaluating and Enhancing LLM Alignment in Mental Health
• 52Singular perturbations and hierarchical learning in two-layer neural networks
• 51@aws-sdk/core — Core functions & classes shared by multiple AWS SDK clients.
• 51@typescript-eslint/types — Types for the TypeScript-ESTree AST spec
• 51How Do Practitioners Build SE Agents? Insights from a Mixed-Methods Study
• 51Reliability Scaling Laws for Quantized Large Language Models
• 51Diversify Diffusion with Temperature Sampling and Variance-Corrective Time Shifting
• 51@aws-sdk/types — Types for the AWS SDK
• 51Capabilities of Claude Fable 5 on Biomedical Challenge Problems
• 51Predictive Divergence Masks for LLM RL
• 51Quantifying the Sources of Instability in LLM-Based Stance Analysis of Public Discourse
• 50Route, Communicate, and Reason: Gated Routing and Adaptive Depth for Efficient Multi-Agent Reasoning
• 503D-DefectBench: A Controlled Factorial Study of Vision-Language Model Evaluation Pipelines for Fine-Grained 3D Generation Defects
• 50Large Language Models for Token-Efficient and Semantic-Preserving Opinion Summarization
• 50Jacobian Conjecture from Wolfram MathWorld
• 50Swift Classes — Inheritance, Override, and the final Keyword 🧬
• 50TypeScript 7 is officially released! 🚨
• 50Meme Monday
• 50lucide-react — A Lucide icon library package for React applications.
• 50BrowserAct vs Agent Browser: A Hands-On Stealth Execution Comparison
• 50reteetzad/Kimi-K3
• 50How To Cut MCP Token Costs? Save Up To 92% At Scale With Code Mode 💎
• 50Graph Neural Networks for RFID-Based Spatial Geometry Inference in Spatial AI Systems
• 50Top 7 Featured DEV Posts of the Week
• 50How to efficiently handle deep pagination and sorting for 12.5 million records?
• 50Métricas de qualidade de software na era da IA
• 50Meme Monday
• 49DEV’s Big Summer Bug Smash is now LIVE! Share $5,000 in cash prizes, skateboards, and more across 20+ winners. 🐛🐞🪲
• 49Your PDFs Are Eating Your LLM's Tokens for Breakfast
• 49@typescript-eslint/typescript-estree — A parser that converts TypeScript source code into an ESTree compatible form
• 49Auditing Belief-Conditioned LLM Agents in Hidden-Information Social Deduction Games
• 49Produto 4 Devs
• 49Lobsters Interview with mitchellh
• 49Distributed Agent System: Fault-Tolerant Collaboration Among Embodied Agents
• 49Diachronic Sample Integration: Robust Tail-Risk Estimation with Generative Models
• 49Join our DEV Weekend Challenge: Passion Edition — $1,000 in Prizes Across FIVE Winners! Submissions Due July 13 at 6:59 AM UTC.
• 49Top 7 Featured DEV Posts of the Week
• 49Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data
• 49Metacognition in LLMs: Foundations, Progress, and Opportunities
• 49Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution
• 49Leveraging unlabelled data for generalizable neural population decoding
• 49The Seriality Gap in Video Diffusion Models
• 49TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale
• 49Lower Bound on the Cumulative Constrained Violation for the OGD+Projection algorithm for Constrained Online Convex Optimization (COCO)
• 49PalmClaw: A Native On-Device Agent Framework for Mobile Phones
• 49Invariant Learning Dynamics of Transformers in Inductive Reasoning Tasks
• 49A Minimalist Retargeting-Guided Reinforcement Learning Recipe for Dexterous Manipulation
• 49A Durability and Cross-Language Transfer Benchmark for a Validated Teaching-Feedback Classification Protocol
• 49A Shortcut to Statistically Steady-State Turbulence with Flow Matching
• 49Linear Independent Component Analysis via Optimal Transport
• 49Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias
• 49Audio-Native Speech Recognition with a Frozen Discrete-Diffusion Language Model
• 49Abstractiveness Metrics for Evaluating Text Summarization: A Refined Formulation with Empirical Validation
• 49Dynamic Resource Allocation for Ensemble Determinization MCTS
• 49Evidence-Backed Video Question Answering
• 49The Spectrum Is Not Enough: When Context Helps Time-Series Forecasting
• 49Diagnosing and Mitigating Thinking Collapse in On-Policy Self-Distillation
• 49Watermark Forensics for Generative Models: An Information-Theoretic Perspective
• 49When does distribution shift break graph neural networks calibration?
• 49Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs
• 49Q-Learning Lab: Teaching Reinforcement Learning Through Learner-Generated Trace Analysis
• 49Faulty Towers, vibe sickness, and the vibe bobsled
• 49MetaPerch: Learning from metadata for bioacoustics foundation models
• 49Trust Before Fusion: QIMG-7 and Source-Aware Resolution for Polluted Multimodal RAG
• 48AdvancedMathBench: A Benchmark Suite for Advanced Mathematical Proof Generation and Verification
• 48Screening of Biosecurity Features in Metagenomic Data with Evo 2 Probes
• 48mutation-testing-metrics — Utility functions to calculate mutation testing metrics.
• 48ai — AI SDK by Vercel - build apps like ChatGPT, Claude, Gemini, and more with a single interface for any model using the Vercel AI Gateway
• 48STEC: Evidence Compression for Deep Search in Open-domain Multi-Hop QA
• 48Claude found a counterexample to the Jacobian Conjecture
• 48@typescript-eslint/parser — An ESLint custom parser which leverages TypeScript ESTree
• 48Input-Aware Dynamic Backdoor Attack Against Quantum Neural Networks
• 48Hierarchical Bayesian Quadrature
• 48Win by Silence: Deletion Non-Monotonicity, Autonomous Exploitation, and Typed-State Gating in LLM Plan Evaluation
• 48LoRA-Based Cascaded Multimodal Fusion for Action Recognition in Medical Training Environments
• 48Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs
• 48AI builder essentials: tokens, context windows and RAG 101
• 48FormalAnalyticGeo: A Neural-Symbolic Based Framework for Multimodal Analytic Geometry Problem Generation
• 48Hindcast: Replaying Prediction Markets to Evaluate LLM Forecasters
• 48mutation-testing-report-schema — The json schema for a mutation testing report.
• 48Imaging-101: Benchmarking LLM Coding Agents on Scientific Computational Imaging
• 48Transformer-Guided Swarm Intelligence for Frugal Neural Architecture Search
• 48Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Models
• 48Earthquaker-AI: A Retrieval-Augmented Generation Framework with Rubric-Based Assessment for Primary School Earthquake Education
• 48Ensemble Controlled-Flow Filtering for Implicit Data Assimilation
• 48AI-accelerated End-to-End Framework for Rapid Professional Upskilling
• 48Multi-Expert Routing for Multi-Domain Low-Resource OCR: A Manchu Case Study
• 48MM-ToolSandBox: A Unified Framework for Evaluating Visual Tool-Calling Agents
• 48Relaxing Faithfulness with Intervention-Only Causal Discovery
• 48mutation-testing-elements — A suite of web components for a mutation testing report.
• 48Can an Old Dog Be Taught New Tricks? Taking LLMs Beyond Sentence Level Translation
• 48Early Adoption of Agentic Coding Tools by GitHub Projects
• 48Detecting AI-Generated Video: A Vision-Language Dual-View Survey
• 48The Dirty Secret Behind AI Agents (Demo 🚀)
• 48The Illusion of Robustness: Aggregate Accuracy Hides Prediction Flips under Task-Irrelevant Context
• 48Introducing Human-Centeredness in AI-Assisted Lexicography
• 48Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models
• 48Improving Wind and Solar Power Prediction with Efficient Wrapper-based Feature Selection: An Empirical Study
• 47Encoder-Side Neuron Identification and Amplification for Acoustic Perception in Large Audio-Language Models
• 47Transforming Rank: How Architecture Navigates the Spectral Pathologies of Depth
• 47StoryTeller: Training-Free Narrative Grounding for Long-Form Audio Description
• 47An Exact Instrument for State Usage in Selective State-Space Models, and the Input-Driven Migration It Reveals
• 47Robustness of Deep Learning Models for PV Power Forecasting under NWP Forecast Errors: A Spatiotemporal and Physically Interpretable Analysis
• 47@aws-sdk/middleware-host-header — [](https://www.npmj
• 47@typescript-eslint/eslint-plugin — TypeScript plugin for ESLint
• 47Lighthouse RL: Sample-Efficient Circuit Optimization via Strategic Reset Points
• 47Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation
• 47Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0
• 47Forgetting Our Way to Shared Meaning: Effects of Forgetting on Conceptual Alignment in a Non-Partnership Coordination Game
• 47How Temperature Shapes Ideological Discourse in Retrieval-Augmented Generation?
• 47Lyapunov Exponent as Physics-Informed Dense Reward: RL Discovery of Stabilization Beyond the Kapitza Pendulum
• 47The Dynamic Verifiable Multi-Agent Human Agentic Loyalty Loop (DVM-HALL) Model and the Net Human-Agent Score (NHAS) in Autonomous Commerce
• 47ViHoRec: A Quality-Controlled Vietnamese Hotel Recommendation Dataset and Cold-Start Benchmark
• 47Evaluating RE Practices for Explainability: Synthesizing Insights from Daimler Truck into an Explainable RE Framework Proposal
• 47From Expressivity to Sample Complexity: Narrow Teachers for Transformers via C-RASP
• 47From Global to Factor-Wise Expert Composition in Discrete Diffusion Models
• 47lobste.rs is now running on SQLite
• 47TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents
• 47Multimodal Empirical Bayes Variational Autoencoders for Joint Longitudinal and Time-to-Event Modeling
• 47Paradoxes of Game Theoretic Equilibria and Price of Anarchy
• 47When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems
• 47@toon-format/toon — Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware encoding of JSON for LLM prompts
• 47Music-to-Dance Generation via Atomic Movements
• 47Constraint-Aware Counterfactual Editing for Aspect-Based Sentiment Analysis
• 47Playful AI in Professional Email: A Field Experiment on Tone and Recipient Engagement
• 47HiFi-LLP: High-Fidelity, Low-Cost Latency Predictors with Confidence for Robust HW-NAS
• 46Miora — Scale your creativity on editable canvas with agent memory
• 46Efficient Sequential Calibration with $O(T^{2/3-ε})$ Error Bound
• 46MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning
• 46Knowledge- and Gradient-Guided Reinforcement Learning for Parametrized Action Markov Decision Processes
• 46NeuralActuator: Neural Actuation Modeling for Robot Dynamics and External Force Perception
• 46LatentFlow: A General Framework for Conditioning Stochastic Processes
• 46DeltaMerge-LowRes: Composing Language and Task Deltas for Low-Resource Adaptation
• 46Contrastive-Collapsed Loss for Flexible and Geometrically Optimal Embeddings and Faster Convergence
• 46Time-Lag-Aware Deep Reinforcement Learning for Flexible Job-Shop Scheduling in PPVC Module Factories
• 46STEP: Career-Path Recommendation via Temporal and Educational Trajectory Modeling
• 46Active Offline-to-Online Reinforcement Learning
• 46Real-time fall detection based on vision for low-power edge platforms
• 46JobHop v2: A Large-Scale Career Trajectory Dataset from Unstructured Resumes
• 46An open-source alternative to iCloud and Google Photos
• 46Accelerated Mixing Time of Randomized Hamiltonian Monte Carlo
• 46CatRetriever: Contrastive Representation Learning for Slab-to-Bulk Retrieval in Generative Catalyst Discovery
• 46An Explainable Agentic System for Detection of Conversational Scams with Summary-Based Memory
• 46What's causing my solr cores to fail to load after an upgrade from solr 9.10.1 to solr 10.0.0?
• 46MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations
• 46UR-VC: Unsupervised Robotic Value Correction for Time-Derived Progress Proxies
• 46VoxENES 2026: Benchmarking Generalization of Speech Spoofing Detectors Against LLM-Era TTS and Voice Conversion
• 46Energy-Based Physics-Informed Form Finding for Clustered Tensegrity Structures
• 46@tanstack/react-start — Modern and scalable routing for React applications
• 46A Multi-Agent System for Autonomous, Fine-Tuning-Free Clinical Symptom Detection: Development and Validation Study
• 46Production and Perception in LLMs: A Token Probability Approach
• 46LLM Judges Can Be Too Generous When There Is No Reference Answer
• 46Beyond the $d^{2.5}$-mixing bound for Dikin walks on polytopes
• 46$\mathtt{Q^2SAR}$: overcoming classical bottlenecks in drug discovery via quantum multiple kernel learning
• 46Evaluating Large Language Models on Misconceptions in Multi-Turn Medical Conversations
• 46Agent Hacks Agent: Autoresearch for Production-Agent Red-Teaming
• 46Think Through a Bottleneck: Hourglass Reasoning for Rigorous Induction
• 46A Self-Evolving Agent for Longitudinal Personal Health Management
• 46A novel unsupervised machine learning strategy to handle multimodal cardiac PET/MRI data
• 46From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence
• 46Deep4ge: DNN Training Trajectories for Fault Detection and Diagnosis
• 46Moral Attitudes of Sentient ASI towards Humanity and Implications for AGI Development
• 46Toward Localizing and Repairing Bias in Transformer Attention Heads
• 46TypeScript Declaration Merging in 2026: Augmenting Third-Party Modules Without Losing Type Safety
• 46Multimodal Semantic-Aware Contrastive Learning For False Negative Mitigation in 3D Medical Imaging
• 46VAIOM: Continuous-Input, Discrete-Output Decoder-Only Financial Sequence Modeling
• 46Plausible Deniability Guarantees for Whistleblowers
• 45Unveiling Complex Collective Behaviors from Simple Rewards