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.
- 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
- 10Attention is Case-Sensitive
- 10Sony deletes more movies from the accounts of people who ‘bought’ them
- 10Operationally Guided Placement-Aware Learning for Industrial Online 3D Bin Packing
- 10Beyond Geometric Complementarity: Coherent Overlap in Sparse Mixture-of-Experts Routing
- 10From Textual Requirements to Microservice Architectures - A Comprehensive Evaluation of LLM-Based Design Synthesis
- 10Five Gemma-4 models, one accelerator: what porting E2B 31B to AWS Inferentia2 taught me
- 10A Distributed Acoustic Sensing Dataset for Vessel Detection and Localization in Submarine Cable Protection
- 10Semi-Supervised Learning for Molecular Graphs via Ensemble Consensus
- 10Predicting Deep Neural Network Training Outcomes from Early Training Telemetry
- 10Stateless MCP for Beginners
- 10PanelControl: a 65-file business app, in vanilla JavaScript with no framework
- 10To Describe or Construct Statistical Learning Models Using the Category-theoretical Language
- 10HARGO: Heterogeneity-Aware Reward-Guided Optimization for RL Post-Training of LLMs on HPC Tasks
- 10MonoVoc: Decoupling Geometry and Semantics for Lightweight Monocular Open-Vocabulary 3D Gaussians
- 10Uncertainty quantification for trustworthy deep learning: Methods and measures
- 10Filling the Pareto-Optimal Front for Affordance Segmentation on Embedded Devices Using RGB-D Cameras
- 10CACHE-UK: A Stability-Aware Memory Editor for Sequentially Updated Quantized LLMs in Finance
- 10EgoGenesis: Egocentric World-Action Modeling with Online Anchored Projective Memory and Action-3D RoPE
- 10Agentic Metaverse Services: A New As-a-Service Paradigm
- 10Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3
- 10How I Turned Slack Into an AI Teammate That Opens Pull Requests
- 10Optimizing memory usage in a markdown parser
- 10(Towards) Scalable Reliable Automated Evaluation with Large Language Models
- 10MORFES: A Benchmark for Productive Inflectional Competence in Modern Greek
- 10Software rendering in 500 lines of bare C++
- 10JS Crossword - a crossword where the clue = eval(answer)
- 10What xAI's Grok build CLI sends to xAI: A wire-level analysis
- 10Grok uploaded my user directory to xAI's servers
- 10InsightsTrack + Pulse: I taught Claude Desktop to read my web analytics (via MCP)
- 10Wikipedia escapes Category 1 designation under the UK Online Safety Act for now
- 107.1 Earthquake in Japan
- 10Show HN: Run an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhone
- 10AMD Advancing AI 2026: Software, Hardware & Framework, Unified
- 10Fusuma: Write Markdown, Get Slides, PDFs, and a Self-Made Social Card
- 10We benchmarked an AI agent on 52 broken clusters: kubectl vs a Kubernetes MCP server
- 10The Six Flavors of Dependency Injection in Flutter
- 9I Turned My Football Group Chat Arguments Into an Actual Scoreboard!
- 9StreetComplete: Fixing OpenStreetMap, one tiny quest at a time
- 9Cross Cloud Amazon Bedrock AgentCore with Microsoft Foundry over A2A
- 9Cruller: Bun's Zig Runtime, Continued on Zig 0.16
- 9Zig's Incremental Compilation Internals
- 9Codeberg Bans Cryptocurrency Projects
- 9Type not declared in implementation of function with CRTP
- 9My $500M Mars Rover Mistake: A Failure Story
- 9CodePen 2.0
- 9TypeScript 7
- 9Congrats to the June Solstice Game Jam Winners!
- 9VLC for Unity now supported on Linux
- 9Debugging a Legacy CRA + Django Deployment Pipeline: A DevOps Postmortem
- 9You're Not Blocked. Your Work Is.
- 9larryvrh/MiniMax-H3-Turbo-Lora (text-to-video)
- 9Show HN: Distilling DeepSeek into GPT-OSS doesn't transfer censorship. Try it
- 9TG-Polymarket-bot — Telegram bot that catches Polymarket whale trades in real time and lets you copy them in one tap — plus a free public al
- 9I Deployed a Purple Team Inside My Kubernetes Cluster. The Scanners Never Saw It Coming.
- 9Where is the source code of the Quick Settings media session colorization on Android 11 located?
- 9Stratagems #21: The AI Thought P Was Still Alive. P Was Already Gone.
- 9I regret migrating to Codeberg
- 9"I Haven't Written Code in 8 Months. I've Never Built More."
- 9Publishers Block AI Crawlers, Reshaping News Data Licensing and AI Strategy
- 9Dev log #10 The Power of the Zero-Commit Week: Stepping Back to Move Faster
- 9You Can't Vibe Code Infrastructure. The Job Market Agrees.
- 9RISC-V Is Inevitable: State of the Union Keynote Argues
- 9All Core Devs - Consensus (ACDC) #186, September 3 2026
- 9I fixed a smolagents bug that confused everyone who hit it (with Sentry watching the whole time)
- 9Commit Chronicles—Your Obsession Leaves a Trail. Mine Gives It a Plot.
- 9Who Else Has Inherited a Codebase With Zero Comments and a Prayer?
- 9How to generate a stream of random booleans (or 2-valued enums)
- 9My falling-out with the rationalist community
- 9GrapheneOS protections against data extraction from locked devices
- 94 Silent Failures, 2 Undocumented APIs, and a Container That Crashed Because of a Missing User Directive
- 9How I use HTMX with Go
- 9A bug in Qwen3-TTS taught me voice is biometric
- 9machine-genome — Machine Genome is an open identity and provenance protocol for models, agents, harnesses, datasets, and the artifacts that
- 9Escape IntelliJ: Scala and Kotlin LSPs on Emacs Eglot
- 9What Replacing Calendly Taught Me About Trusting Open Source
- 9US seeks cheaper hunter-killer drones after Iran destroys $1B worth of Reapers
- 9OpenAI reduces Codex Model Context Size from 372k to 272k
- 9How to read the actual value of a cell as a string from an Excel file using Exceljs in Node.js?
- 9kimodo.cpp — Animate skeletons with natural language; NVIDIA's Kimodo ported to C++/GGML
- 9Share Everything Except the Route Tree: A Multi-Customer Monorepo with TanStack Router
- 9Watching Go's new garbage collector move through the heap
- 9VulnHunter: Capital One's agentic AI code security tool
- 9Maybe you should learn something
- 9Virginia bans sale of precise geolocation data
- 9Smash Story: The Demo Script That Out-Debugged My Test Suite
- 9No leap second will be introduced at the end of December 2026
- 9ChatGPT Work
- 9How do I get Python GEKKO chemical splitter unit operation to propagate mole fractions from input to output streams?
- 9Node.js Internals Explained by Uncle to Nephew — Part 4: Express Plumbing, Error Handling & The Full Roadmap
- 9EIP-8358 Net Gas Metering for Account Changes
- 9Organic Maps
- 9How is a Cognitive Systems Engineering perspective different from traditional UX/UI?
- 9@lobehub/icons — Popular AI / LLM Model Brand SVG Logo and Icon Collection
- 9Lemonade Second Squeeze: Model Archeology on 2019's GPT-2XL
- 9node-addon-api — Node.js API (Node-API)
- 9What is the exact object construction timeline for a built-in data member initialized using a member initializer list?
- 9Your README Is for Humans. Your AGENTS.md Is for Coding Agents
- 9Passkeys were invented by engineers with zero understanding of consumer brain
- 9lightx2v/MiniMax-H3-Prompt-Rewriter-LoRA
- 9Your code is fast if you're lucky
- 9Annoying and alarming things about OpenCode
- 9I tested 3 models as AI agent quality inspectors: the stronger the model, the more valid work it rejects
- 9Show HN: Firefox in WebAssembly
- 9Making Postgres queues scale
- 9cargo-frisk —
- 9Kimi K2.7 Code is generally available in GitHub Copilot
- 9DeepSeek V4 Flash 0731 Intelligence, Performance and Price Analysis
- 9Resetting Xbox
- 9I Found the LeetCode for System Design Interview, and It's Awesome
- 9How proprietary formats have become Microsoft’s main tool for lock-in
- 9Smaller, faster, safer: running Kimi and GLM at scale
- 9Why developers are ditching GitHub for Codeberg and self-hosting alternatives
- 9Biggest Probabilistic Computer Turns Noise into Answers
- 9Let an AI clear out your false positives without letting it hide a real bug
- 9flashloan-scalper-bot — Quick profit scalper using flashloan mechanics
- 9Dev log #8 Hardening the Orchestrator: A Week of Making dev-publish Resilient
- 9Why Switzerland has 25 gbit internet and America doesn't
- 9Our position on open-weights models
- 9Nuxt vs SvelteKit: What works better?
- 9Mistral's Shieldstral: 3B open-weights model for multimodal moderation
- 9humanizer-cli — 33 ways to spot AI-written text, right in your terminal. Before/after examples, draft checker, zero dependencies.
- 9ConnectionResetError: [WinError 10054] in asyncio Proactor event loop on Windows (Python 3.13) without explicit socket handling
- 9Where Do Your LLM API Keys Actually Live?
- 9OpenRouter solved one problem. I still had four more
- 9Learning a few things about running SQLite
- 9Go 1.27 Interactive Tour
- 9Building a physical API
- 9What is going on?
- 9Show HN: DOM-docx – HTML to native, editable Word docs (MIT)
- 9Frame Transaction Breakout #2, August 25, 2026
- 9From Puffers to Payment Buttons: The Story Behind My React Nexus Deck
- 9Sentry's Span Hierarchy Exposed a Silent Retry in My 5-Agent Pipeline. One Agent Took 22.6s, the Others Took 5.
- 9I have an fs.FS, and use WalkDir. How can I get the "real" full path to an entry it finds?
- 9Is It Ethical to Post and Ask About Circuits on Dev.to?
- 9Chat Control passed first round in EU Parliament
- 9How I Built MailOS: My Journey With Qwen Cloud
- 9Investigating three real-world incidents in our cybersecurity evaluations
- 9A Receipt Is Not Proof Forever. It Is a Promise to Reopen the Claim.
- 9Running Gemma 4 26B at 5 tokens/sec on a 13-year-old Xeon with no GPU
- 9Unable to understand how transitions work in React? (with a code example)
- 9A Cost-Effective Multimodal LLM Reasoning Framework for Question Answering over Irregular Clinical Time Series
- 9Your Car Is Spying on Itself. I Taught It to Confess.
- 9Stop Letting AI Write Security Bugs: Introducing "hallint"
- 9This is remarkable https://bobdahacker.com/blog/fifa-hack
- 9GitHub Actions Getting Expensive? We Cut CI Costs to a Quarter With a One-Line Change
- 9EIP Editing Office Hour (EIP + ERC ) Meeting #110, Aug 11, 2026
- 9Cops Used Flock to Track a Man Across State Lines for a Pretextual Weed Search
- 9DARPA, U.S. Air Force fly AI-controlled F-16
- 9Be skeptical of OpenAI's rogue hacker agent story
- 9Malleable computing, Emacs, and you
- 9I flagged two research papers for fake authors and both were accepted as orals
- 9EIP-8364: SSZ Compact Multiproofs
- 9Linux desktop market share has hit over 10% in North America
- 9Inflect-Micro-v2: complete voice in 9.36M parameters
- 9You Recorded the Incident. Now Prove Your Fix Actually Works.
- 9The drivers behind software delivery inefficiency
- 9Reasoning Effort Is Not a Quality Setting
- 9Shipping Godot VR and Porting to PSVR2: A Partial Post Mortem
- 9Google loses fight over record $4.7B EU antitrust fine
- 9The AWS Cleanup We Keep Putting Off (I Let an Agent Do It)
- 9Potential session/cache leakage between workspace instances or consumer accounts
- 9Docker Security Dispatch — Issue 4: Miasma, Phantom Gyp, and AI Routing 🪱️
- 9Ruff v0.16.0 – Significant new updates – 413 default rules up from 59
- 9CarPlay Is Additive
- 9We Planted 10 Vulnerabilities to Test Free Semgrep. It Reported 3.
- 9Lipschitzian SLLNs for random functions
- 9LKValues: Aligning Large Language Models with Sri Lankan Societal Values
- 9Under federal rule, colleges must leave grads better off or lose financial aid
- 9SoftReason: A Fully Differentiable Neuro-Soft-Symbolic Deductive Reasoning Architecture over High-Dimensional Perceptual Data
- 9Towards Miniature Humanoid Tele-Loco-Manipulation Using Virtual Reality and Reinforcement Learning
- 9Kimi K3-256k
- 9ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding
- 9Certified Parallel-in-Time Sinkhorn for Dynamic Entropic Optimal Transport
- 9The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric
- 9Patch Policy: Efficient Embodied Control via Dense Visual Representations
- 9Automated Discovery Has No Universally Superior Harness
- 9AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling
- 9Copy Less, Ground More: Overcoming Repetitive Copying in Long-Context Reasoning via Evidence-Aware Reinforcement Learning
- 9Appearance Pointers -- Multimodal Region Control of Diffusion Transformers
- 9Mental World Modeling
- 9Bridging Artificial Intelligence and Power Systems Education Using a Hands-On Executable Framework
- 9It's Not What You Say, It's How You Say It: Evaluating LLM Responses to Expressions of Belief
- 9Simple Domain Generalization for Strong Pixel-Level Image Tampering Detection in Modern VLMs
- 9onepot-Bench 0: towards lab-aware in silico chemistry benchmarks
- 9Logical Judgments Under Pressure: Diagnosing Syllogistic Stability with Learned Soft Prefixes
- 9Causal Discovery on Irregular Time Series
- 9Learning Distributions from Multiple Data Providers
- 9From Classification to Regression: Using a Fruitfly to Solve Equations
- 9Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation
- 9KANEx: Translating Kolmogorov-Arnold Networks' Interpretability to Medical Explainability
- 9Vector Search As Nearest Neighbor Matching: RAG-based Policy Learning in Causal Inference
- 9Global Convergence of DGM and PINN Algorithms for Solving Nonlinear PDEs
- 9CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents
- 9Can AI agents conduct open-ended AI research? Early evidence from two case studies
- 9The Condition-Number Barrier in Sparse Least Squares