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.

• 7Saga Pattern Explained: Distributed Transactions in Microservices
• 7I Built a Zero-Dependency Env Validator with Full TypeScript Inference - Here's Why
• 7The Missing Row: Auto-Provisioning Derived Records Without the Race Condition
• 7Just for Fun: Fear and Loathing in the Age of Coding Agents
• 7SDR Is the New Wireshark: Sniffing the Sub-GHz Spectrum from Your Desk
• 7Node.js Internals — An Uncle-Nephew Conversation (Hindi)🍵
• 7Enterprise Development Isn't Hard Because of Code
• 7I built Commitea: Git and GitHub explained in Spanish, with an interactive visualizer
• 7Clear the Lineup — Astro's `popover` Attribute Had No Way to Say False
• 7Ensamblando DotNet IL
• 7Ask HN: What are your favorite blogs not about AI?
• 7Apple defeats liability for not scanning iCloud for CSAM
• 7Integrating Lambda Durable Functions into a Step Functions Workflow
• 7Deterministic Guardrails: Prompts Steer, Hooks Enforce
• 7What Happens When Everyone Can Build Apps But Nobody Understands Them?
• 7Which AI APIs go down most? Data from 6 weeks monitoring 77 services
• 7If These Letters Are Trying To Communicate With Me, They Should File Their Own Bug Report ;)
• 7Building a real-time Crystal app with Kemal — where privacy is a server invariant
• 7Map of the world's great castles and fortresses
• 7Coding Agents Evolved. Our Repositories Didn’t.
• 7Designing Your Own AI Harness: A Deep Dive Into the Architecture of Agent Loops, Tools, Context, and Control
• 7*This is a submission for [DEV's Summer Bug Smash: Clear the Lineup](https://dev.to/bugsmash) powered by [Sentry](https://sentry.io/).*
• 7I Built a Local RAG Assistant with Ollama, ChromaDB and LangChain. Here's What I Learned
• 7I Rewrote a OneNote MCP Server in TypeScript — Here's What I Learned About Microsoft Graph Auth
• 7Race Recap Radio — I turned my 10K into a hype sports broadcast
• 7Clear the Lineup: Killing a Silent, Three-Cause Rendering Bug in a Flutter + Mapbox Noise Map
• 7How do I get a value from a tkinter scale/slider whilst when it is in a function?
• 7Founding Lead Playbook: Running Product, Architect & Engineering with AI Agents + 2 Humans
• 7Laguna S 2.1
• 7EU fines Google €890M for competition breaches over search and apps
• 7Gemma4 DevOps In Action
• 7Building SaarDB, Part 3: Compaction
• 7Debugging Deployments with Gemma 2B, TPU v6e-1, MCP, and Antigravity CLI
• 7Build One AI Tool Server, Call It From Three Different Agents (MCP Explained)
• 7EIP Editing Office Hour (EIP + ERC ) Meeting #107, July 21, 2026
• 7Why I Ditched Socket.IO for Raw WebSockets (And What I Learned)
• 7Software's Second Free Lunch
• 73D-Aware VLMs with Implicit and Explicit Geometries
• 7Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models
• 7RoboTTT: Context Scaling for Robot Policies
• 7MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators
• 7Death of the Status Update: Why 55% of Americans Stopped Posting on Social Media
• 7SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions
• 7PagedWeight: Efficient MoE LLM Serving with Dynamic Quality-Aware Weight Quantization
• 7Online Neural Space Time Memory for Dynamic Novel View Synthesis
• 7Expanding Flow Maps
• 7HTTP gets a QUERY method so complex searches can stop pretending to be POST https://www.theregister.com/devops/2026/07/13/http-gets-a-query-method-so-complex-searches-can-stop-pretending-to-be-post/5270192
• 7A Blueprint for Equilibrium-Based Differentiable Continuous-Variable Thermodynamic Computing
• 7Cluster-Aware Matching via Laplacian Optimal Transport
• 7GraphVid: Interactive Graph-Controllable Video Generation
• 7Barzilai-Borwein Fails Superlinear Convergence on an Open Set of Quadratics for Every Dimension $n\geq 4$
• 7Physics-enhanced reinforcement learning for real-time optimal control of dynamical systems
• 7Pretraining Data Can Be Poisoned through Computational Propaganda
• 7Synthetic data generation framework for quality control automation in gravure printing
• 7Evaluating Open-Weight LLMs for Generating Structured Threat Information for Autonomous Vehicle Vulnerabilities
• 7SceneBind: Binding What and Where Across Vision, Audio and Language
• 7Surprisal Theory is Tautological (without Rational Grounding)
• 7Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents
• 7Decoding Market Emotion from Blockchain Activity: A Data-Driven Sentiment Classifier
• 7Beyond Sufficiency: Time Series Explanation with Counterfactual Necessity
• 7The Hidden Part of Refresh Token Implementation that every developers should know
• 7SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
• 7MedGame: Storytelling Gamification Empowered by Large Language Models for Medical Education
• 7teLLMe Why (Ain't Nothing but a Jam): Exploratory Causal Analysis of Urban Driving Data
• 7When Does Muon Help Agentic Reinforcement Learning?
• 7Bridge Evidence: Static Retrieval Utility Does Not Predict Causal Utility in Multi-Step Agentic Search
• 7Behaviour-Conditioned Neural Processes for Adaptive Residential Short-Term Load Forecasting
• 7An Exam for Active Observers
• 7AutoSynthesis: An agentic system for automated meta-analysis
• 7Graph Learning on Ensembles of Cyclic Peptides: An Investigation of Molecular Ensemble Modeling
• 7Checkout TalknDo for the #devchallenge #weekendchallenge on the Solana track
• 7First atmosphere found on Earth-like planet in habitable zone of distant star
• 7Your Career Matters. So Does the Person Building It.
• 7Unsupervised Consensus-Based Anomaly Detection for Spatiotemporal Malaria Incidence in Ghana
• 7Beyond Sycophancy: Structured Resistance and Compliance in LLM Moral Reasoning
• 7Mutable Low-Rank Sketches for Retrain-Free Recommendation
• 7OpenForgeRL: Train Harness-native Agents in Any Environment
• 7Beyond the Leaderboard: Design Lessons for Trustworthy Multimodal VQA
• 7Visual Contrastive Self-Distillation
• 7TikStance: A Multimodal and Hierarchical Dataset for Multi-target Stance Analysis in TikTok Political Conversations
• 7MIRROR: Learning from the Other View for Multi-Modal Reasoning
• 7X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment
• 7With an AI agent, the answer is the last place the bug shows up
• 7Neural solutions of coupled ghost and gluon Dyson--Schwinger equations in Landau gauge
• 7PRISA: Proactive Infrastructure LiDAR Framework for Intersection Safety Assessment
• 7Language Identification via Compositional Data Analysis: A Linear-Time Classifier Based on Log-Ratio Geometry
• 7AI coding agents still write your SDK's old API — so I built a type-checker to measure it
• 7The Boundaries of Automation: A Theory of Persistent Human Participation
• 7In-Place Tokenizer Expansion for Pre-trained LLMs
• 7Data Driven Block Replacement Scheduling
• 7Zero-Flow Two-Sample Tests
• 7Browser OS Redefined: The Desktop Metaphor Doesn't Quite Fit a 5" Screen Browser
• 7DONDO: Open w2v-BERT Speech-Recognition Base Models for African Languages
• 7We Pulled a Rule From Our AI Linter — Here's Why It Made the Tool Better
• 7Learning Standard Model structure from LHC data with Riemannian flow matching
• 7Windowed-MTP: Removing the Full-Context Draft-KV Tax at Million-Token Context
• 7sudo 'schland just give me my data
• 7When Words Are Safe But Actions Kill: Probing Physical Danger Beyond Text Safety in Hidden-State Risk Space
• 7Improving Improved Kernel PLS
• 7NeuronSoup: Evolving Asynchronous, Shared-Neuron Temporal Graphs without Backpropagation
• 7I turned my phone into a remote deck for my Windows laptop — no cloud, no accounts, one npm start
• 7Symbal: Detecting Systematic Misalignments in Model-Generated Captions
• 7'Local' Solves Where Your Data Goes. It Doesn't Solve What Your Agent Does
• 7ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing
• 7When Do Multi-Agent Systems Help? An Information Bottleneck Perspective
• 7I Built My Own Text Editor
• 7ToolSciVer: Multimodal Scientific Claim Verification with Visual Tool Augmented Reinforcement Learning
• 7A Methodology for Auditable Trustworthiness Levels in AI Lifecycle Governance
• 7Expanding the Lexicon of Ge'ez Based African Languages: A Comparative Study of Amharic and Tigrinya
• 7Delocalization of bias in unadjusted Hamiltonian Monte Carlo and underdamped Langevin
• 7GS-Agent: Creating 4D Physical Worlds With Generative Simulation
• 7BadWAM: When World-Action Models Dream Right but Act Wrong
• 7Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation
• 7MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
• 7Improved lower bounds for the Shannon capacity of odd cycles
• 7CRAFT: Clustering Rubrics to Diagnose Weak LLM Capabilities and Generate Targeted Fine-Tuning Data
• 7Self-Evolving Human-Centered Framework for Explainable Depression Symptom Annotation
• 7Mask-Aware Policy Gradients for Diffusion Language Models
• 7Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content
• 7Subjective Risk Decomposition: A New View for Uncertainty Quantification
• 7Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems
• 7Plover: Steering GUI Agents through Plan-Centric Interaction
• 7Artificial Epanorthosis: Why large language models overuse a classical rhetorical figure, and how to mitigate it
• 7I Didn't Memorize the Android ViewModel, I Derived It From 8 Problems( Interview Prep)
• 7Harmonizing AI Safety Thresholds
• 7Can We Trust Item Response Theory for AI Evaluation?
• 7Toward Generalizable Cognitive Impairment Detection with Speech-Based Multimodal Large Language Models
• 7The Honest Quorum Problem: Epistemic Byzantine Fault Tolerance for Agentic Infrastructure
• 7Toward Continuous Assurance for the Democratization of AI Agent Creation in Industry
• 7GSoC Midterm Update: Rebuilding BLT for a Cloudflare-First Future
• 7🏗️ Akhouri Systems: 4 apps, 1 thirteen-year-old kid, 0 employees
• 7Meta's AI models are powering the first wave of Genesis Mission projects
• 7S&P Global has lowered Oracle’s creditworthiness from BBB to BBB-
• 7RTS Smoother-Guided Learning of Physics-Based Neural Differential Models
• 7What, Where, and How: Disentangling the Roles of Task, Language, and Model in Code Model Representations
• 7The Moderation System That Was Running Perfectly — On Nobody
• 7T^2MLR: Transformer with Temporal Middle-Layer Recurrence
• 7Understanding Reasoning from Pretraining to Post-Training
• 7Benchmarking Multimodal Large Language Models for Scientific Visualization Literacy
• 7Compact Latent Coordination for Autonomous Vehicles at Unsignalized Intersections
• 7The Beam Engine
• 7Introducing Agent-Up: run multiple agent-built versions of your web app at once
• 7Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation tasks
• 7Linear representations of grammaticality in neural language models
• 7Ghostel.el: Terminal emulator powered by libghostty
• 7Finite-Sample Coverage Audits for High-Recall Candidate Generation: Certification and Learning-Theoretic Design
• 7DADiff: Diffusion-Driven Cross-Domain Policy Adaptation for Reinforcement Learning
• 7Neural spectroscopy of AlphaFold2 reveals encoded protein conformational landscapes
• 7Error Certificates for KV-Cache Eviction via Randomized Design
• 7MedFailBench: A Clinician-Built Open-Source Benchmark for Medical AI Safety Boundary Inspection
• 7Controlling Implicit Shortcut Reliance in L2 Spoken English Auto-markers
• 7Pick-to-Learn Calibration of an MPC Policy for an Origin-to-Destination Flight Problem
• 7The Industrialization of Research ; On AI-Driven Science and Its Consequences
• 7I Wasn't Allowed Prompting ChatGPT During My Chalk Talk: This Is Discrimination (2025)
• 7Show HN: Microsoft releases Flint, a visualization language for AI agents
• 7Thinkink: 2D Spatial Ink-native Interaction with LLMs
• 7Are we offloading too much of our thinking to AI?
• 7Physics-Based Deep Spatiotemporal Hyperlocal Radar Nowcasting with a Multi-Variable U-Net for High-Resolution Precipitation Forecasting
• 7Scaling Behavior Foundation Model for Humanoid Robots
• 7On-Policy Delta Distillation
• 7AREX: Towards a Recursively Self-Improving Agent for Deep Research
• 7Private healthcare makes industries less innovative. It's time for change
• 7HCIG: A Hierarchical Cross-Modal Incongruity Graph Network for Multimodal Sarcasm and Cyberbullying Detection
• 7Timelock Account recovery: A trust minimized recovery system for Smart Accounts
• 7Detecting LLM-Generated Tokens in Human--LLM Coauthored Text
• 7JoyNexus: Service-Oriented Multi-Tenant Post-Training for VLA Models
• 7Frontier Language Models Struggle to Copy: Text Can Be Better Viewed in 2D
• 7Test-Time Scaling via Error Localization
• 7Post-Quantum (PQ) Interop #48, July 22, 2026
• 7RUMBA: Russian User Memory Benchmark
• 7KroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion Transformers
• 7When Trivia Is Not Trivial: Everyday Knowledge Failures in Multilingual LLMs
• 7Climate-resilient electric vehicle charging infrastructure for sustainable cities: An interpretable causal-ensemble framework for preventive maintenance and low-carbon mobility
• 7LLM-Powered Agentic AI for 5G/6G Networks: A Tutorial and Survey on Architectures, Protocols, and Standardization
• 7Spatial Normalization for Cross-Domain Retinal Layer Segmentation in Optical Coherence Tomography
• 7Concept-Guided Spatial Regularization for World Models in Atari Pong
• 7Agent-Guided Relational Concept Discovery: Toward Interpretable Surgical Margin Assessment
• 7400+ downloads, 0 revenue, and why that's actually fine for now
• 7When Model Merging Rivals Joint Multi-Task Reinforcement Learning: A Task-Vector Geometry Analysis
• 7Adaptive Identity Anchoring: Closed-Loop Keyframe Placement for Synthetic Paired Supervision in Video Face Swapping
• 7Token Budget Saturation and Mechanistic Early Detection of Reasoning Non-Convergence in Chain-of-Thought Models
• 7Frontier AI performance across the business disciplines: a case-grounded benchmark of knowledge work and analytical reasoning
• 7One More Year -> The Documentary I Never Filmed
• 7Fable 5 Hype: Fangirling with Datasets to Build a Lakers Dashboard
• 7Data structures your CS degree kind of glossed over
• 7Deep and Probabilistic Models for Gene Regulatory Network Inference
• 7Context-weighted Discrete Flow Matching
• 7Semantic-Aware Task Clustering for Constructive and Cooperative Multi-Tasking
• 7My USB Drive Has a Hidden Encrypted Vault
• 7Loop the Loopies!
• 7DELUGE: Towards Continental-Scale Daily Pluvial Flood Damage Prediction via Interpretable Conditioning on Foundation Model Embeddings
• 7An Evaluation Framework for Structured Audio Captions Validated by Controlled Perturbations
• 7Bridging the Gap Between Plausibility and Admissibility: Constraint-Aware Flow Maps for Dynamic Graph Systems
• 7PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning
• 7Learning in Infinitesimal Non-Compositional Sketches
• 7Logical Regression for Planning with Axioms
• 7Long-Context Fine-Tuning with Limited VRAM
• 7Euclid-MCP: A Model Context Protocol Server for Deterministic Logical Reasoning via Prolog
• 7SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery
• 7GLM 5.2 is nearly as accurate as a human book keeper