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.
- 21ProCARE: Real-World Study Automation via Profile-Grounded Evidence Contracts
- 21EventLens: Event-Structure Reinforcement Learning for Video Understanding
- 21DeepThink: A Conceptual Model for Knowledge-Addressable Recurrent Language Modeling
- 21Interactive 4D Volumetric Liquid Forecasting under Moving-Solid Interaction
- 21Think Before You Speak: Enabling Training-Free Latent Communication Between Language Models
- 21EschaLabs/Qwen3.8-27B-Escha-W2 (text-generation)
- 21Fisher information and the geometry of memorization in neural networks
- 21Uncovering Robustness Weaknesses in LLM Agents via Persona Evolution with Task-Integrity Constraints
- 21Testing In-App Chat and Customer Support Flows in Delivery Apps
- 21Show HN: Jevman – AI decision models play Pac-Man
- 21FreeBSD ate my ram
- 21@aws-sdk/middleware-websocket — [](https://www.npmjs.co
- 21Teaching Claude Code to Paint: A Stateful Image-Editing Skill Built on Gemini's Interactions API and MCP
- 21Stratagems #10: Lena Watched a Team Adopt Her AI Template. Leo Didn't Know the Knife Was in the Contract.
- 21'AI' is Not a Tool
- 21Cron Jobs in C from Scratch
- 21‘Farewell, Etaoin Shrdlu’
- 21Human mathematicians are being outcounterexampled
- 21empero-ai/Qwen3.8-27B-Ridge-GGUF (image-text-to-text)
- 21Show HN: Glashütte Trash Clock – A 30-minute pendulum clock made from trash
- 21It Was Just a Patch Update. What Could Possibly Go Wrong?
- 21A road to Lisp: Why Lisp
- 21Amiga-Inspired AROS Goes Bare Metal on Raspberry Pi
- 21Is /[\s\S]/ the same as saying /.|\n/ in regex
- 21A Vision for Cargo
- 21Build a contact form with Astro and Resend
- 21Repaint vs Reflow: A Simple Explanation
- 21Gitolite
- 21Has the audience for technical articles dropped?
- 21Finding Nemo: Why BFS is Your Underwater Guide
- 21Can compiler ignore ill formed parts of the template body that are never used
- 21John C. Dvorak has died
- 21From Open Source to Paid Product: Is AI Accelerating the Shift?
- 21Crafting clean code alone won't save you or make you stand out. That's not the real edge anymore. Become a street-smart coder instead.
- 21Twenty Years of Pandoc
- 21Claude Code Git Integration in 2026: How the Agent Reads Diffs, Stages Hunks, and Decides When to Commit
- 21I Built a Canny Alternative — Then Realized the Feedback Board Was the Easy Part
- 20Frappe v16.35.0: OAuth password grant returns invalid_grant while /api/method/login accepts the same credentials (works on v16.33.1)
- 20Student teacher arrested for private Snapchat message
- 20Don't be a meat proxy
- 20✨Cool Effects, TTS, and Fun Animations (AI Avatar v15: VS Code and Chrome Extension)
- 20Code is clay now
- 20Five things I found in Google's Agent Registry and Agent Gateway that aren't in the docs
- 20Towards Understanding LLM-Based Log Anomaly Detection: An Empirical Study of Performance, Efficiency, and Robustness
- 20Equation discovery with Bayesian tree-adjoining grammars
- 20Brenier Meets Adversarial Training: Optimal Transport Geometry for Robust Learning
- 20Programs-of-Layers in LLMs through the Lens of Cortical Areas
- 20A Safety-Bounded SDC-to-MCP Gateway for Medical AI Agents
- 20log is non-monotonic in PHP and Lua
- 20Kill the Cookie Banner
- 20Open Vocabulary Domain Unlearning
- 20Mutable Transcripts: Mitigating Context Pollution through Editable Conversation State
- 20Progressive Memory Transformer: Memory-Aware Attention for Time-Series
- 20DyMD: Preserving Interaction Dynamics through Distribution Matching Distillation in Few-Step Video World Models
- 20Stale-Document Poisoning: When Outdated Retrieval Overrides Correct Model Answers
- 20The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models
- 20Bridging Body and Brain: Gene-Driven Morphology--Control Co-Design
- 20CG-HAF: An Interpretable Global-Local Lesion-Burden Fusion Framework for Ordinal Acne Severity Grading in Agentic Skincare Support
- 20More Sensors Only One Field: Rethinking Continual Spatio-Temporal Forecasting
- 20An empty alarm window makes APPROX_COUNT_DISTINCT fail with a HyperLogLog error
- 20AgentXploit: Autonomous Repository-to-Runtime Red-Teaming for AI Agents
- 20Born Against, or why hobby programming communities are aggressively against LLM usage
- 20[Boost]
- 20LUCID: Learning Under Confounding for Inference and Discovery in Time Series
- 20Towards VLA-Dreamer: Refining VLA Behavior Using World Models
- 20When was the last time you Google or open StackOverflow when stuck?
- 20Plastic mechanical computer from 1963: The Digi-Comp 1 [video]
- 20Benchmarking Attention for Tabular Foundation Models
- 20Geometric Moment Contraction for Stochastic Nesterov Acceleration
- 20Beyond Approved Actions: Runtime Validation of Persistent Outcomes in Agent Workflows
- 20[Boost]
- 20UniAR: A Unified Framework for Autism Recognition Enhanced by Multi-View Prompt Learning
- 20Why Alzheimer's Speech Screening Fails to Generalize: Bridging the Deployment Gap via Cross-Corpus Evidence Anchoring
- 20Softmax Reparameterization for Output-Head Quantization
- 20G2MAF: Test-Time Gradient Guidance for Multi-Agent Flow Policies
- 20Skills vs. fine-tuning (or, why my kids are terrible at putting away laundry)
- 20Code Smell 321 - Getter Piggybacking
- 20What Developer Experience Actually Means
- 20AWS Has Two Iceberg REST Catalogs: What Each One Actually Serves
- 20BlazorMemory 1.0 is out. Ten months, 14 packages, and what I got wrong along the way.
- 20Your Integrity Checks Are Watching the Wrong Layer
- 20I Built an AI That Remembers the Promises We Forget
- 20Resource-Optimized and Energy-Aware Agentic AI Framework Anchored on Blockchain for Secure Software Supply Chains
- 20How I finally understood the Single Responsibility Principle
- 20Notes I Kept While Moving a Project to Angular 21
- 20MA-WAM: Multi-Agent World-Action Model for Test-Time Planning
- 20The Emotional Journey of Deploying on Friday
- 20Gemma 4 on Amazon SageMaker: QAT Weights Decode 2.05x Faster Than bf16 on One L4
- 20What I learned training an ACT policy for the LeRobot SO-ARM101
- 20OpenBSD 7.8 を 7.9 へ アップグレード
- 20Scaling NumPy on Free-Threaded Python
- 20Slow productivity
- 20Cognitive Skills in the Age of AI: Computing Students and Experts Perceptions
- 20Week 9: Verifying the Token
- 20How I finally undestood what loosely coupled modules are
- 20Rent the Cores, Keep the Phone: Building LineageOS 24 on EC2 and Iterating at Home
- 20I switched my nine broken RimWorld mods back on to see if an agent could find them
- 20Telstra outage explained: how one GPS card set the network to 2006
- 20I've built three small, AI-powered, open-source tools in my spare time and am sharing them here.
- 20OpenBSD Upgrade 7.8 to 7.9
- 20Thread Claims Interoperability. Your Network Has Three Meshes.
- 20The Tragedy of the Clean-Handed Auditor
- 20Running Gemma 4 on EC2 G5g: Graviton2 AMD with NVIDIA GPU
- 20Identifying Scientists on X
- 20MLH Hack At Home 2020: Hearth
- 20RESCUE: Is This Alarm Worth Acting On? Counterfactual Evaluation of VLA Runtime Monitors
- 20MoSAR: Mixture of Semantic Attention Regimes for Learning Adaptive and Approximable Attention Geometries
- 20Agentic Limit Order Books: Phase Transitions and Market Impact
- 20Heap & Priority Queue: The Matrix of Efficient Searching
- 20Which Part Was Me?
- 20Installing Rust for vLLM on Graviton: a G5g walk-through 🦀
- 20A guide to proper semantic markup for blog posts
- 20How my personal side project is becoming a professional tool
- 20[Boost]
- 20Retrieval-Augmented Multimodal Language Model with Heterogeneous Evidence Integration for Clinical Prognosis
- 20FedPCD: Priority-Constrained Federated Aggregation
- 20Apache Data Lakehouse Weekly: August 10 to 18, 2026
- 20[Agent Platform in Practice (4)] Towards Cloud Two-layer Decoupling and Full Persistence: Completing the LINE AI Business Card M
- 20The Estian Tattler: a gossip rag for my RimWorld colony that has to cite the save file
- 20Beyond Temporal Proximity: Explanatory World Models for Credit Assignment in Reinforcement Learning
- 20Java Collections Framework: When to Use What – The Fellowship of the List
- 20Humanize MLE Agents: Multi-Agent Session Alternation Beyond Single-Agent Limits
- 20Proactive Agentic Orchestration
- 20Branching On-Policy Distillation
- 20A Scalable Learned Iterative Solver for Nonlinear MPC via Temporal Decomposition
- 20A Local Agentic AI Framework to Generate Edge Case Scenarios for Safety Assurance
- 20Thoroughly Understanding C++ ABI
- 20Harmonic analysis and circuit approximation of Sobolev functions on quantum input spaces
- 20A Better Metric Will Not Save You: What You Compare Beats How You Compare It
- 20It's Got What Content Craves: Sanity, Built for the People of Idiocracy
- 20AT&T's very rare Security-Plus Telephone
- 20When MLLMs miss what humans read: diagnosing and learning to read squint text
- 20SqueezeBench: Saturation-Resilient Evaluation of Mathematical Capability
- 20Towards Enriching Design-Time Models with Evidence from Simulation and Operational Activities
- 20Agentic Large Language Models
- 20Oído: Open-Vocabulary Speech Recognition on a $5 Microcontroller without a Neural Accelerator
- 20Learning by Compression: Risk Estimates Attain the Law-of-Large-Numbers Rate
- 20Revisiting Accent Classification with DistilHuBERT: Speaker-Disjoint Evaluation and Cross-Corpus Generalization
- 20Collective Autonomous Vehicle Routing Needs Social Awareness for Coexistence with Human Drivers
- 20Rollout-Time Intervention: Unlocking Agentic Reinforcement Learning Beyond Policy Limits
- 20Local Diagnostics of Learned Event Representations for Anomaly Detection at the HL-LHC
- 20PPG-Bench: A Unified Benchmark for PPG Foundation Models
- 20CNN-Transformer with Sigmoid Label for High-Resolution Sub-Degree DOA Estimation
- 20Does Financial Speech Need Continual Learning Regularization? A Study of EWC and mini-KFAC on Earnings Call ASR
- 20One Thing Leads to Another: The Essentials of Time Series Causal Discovery
- 20Congrats to the GitHub Finish-Up-A-Thon Challenge Winners!
- 20Web$hell: A Unified Interface for Agentic Web Access
- 20In-Context Learning for System Identification: Probabilistic Formulation, Long-Sequence Handling, and Benchmark Validation
- 20Accelerating Linear Bandits with Persistent Candidate Sets
- 20Desertification Forecasting in Semi-Arid Regions: Using Deep Learning to Probe the Observability Limits of Land Degradation Dynamics
- 20Why Linear Models Can Still Work in a Complex and Changing World
- 20Everyone Should Know SIMD
- 208088 MPH: How it came about
- 20The Bug That Threw No Errors: How a Repeat-Trial Guard Silently Killed Our Free Trial Funnel
- 20From Raw Signals to BlocSignal: Taming Reactivity for Enterprise Scale
- 20TypeScript 6.0 `--noEmit` and Type-Only Builds: Why Your CI Pipeline Should Never Call tsc for Output Again
- 20TypeScript Generic Constraints in Depth: `extends`, `keyof`, and the Patterns That Prevent Runtime Errors
- 20Gemini Canvas Demonstrates Parameterized 3D Design and STL Export Workflow
- 20Building Groovie, an Advanced Web-Based Drum Machine / Beat Sequencer
- 20Zig Creator Calls Spade a Spade, Anthropic Blows Smoke
- 20Exercises in benchmarking and evals, part 7: DeepSWE, Senior SWE-Bench, napkin math, and winter tires
- 20AR And VR In Java: ARKit, ARCore, And A Virtual Room You Can Debug
- 20Dmitri Gaskin on jQuery (2008)
- 20Why Programmers Hate LinkedIn?
- 20Asking Authors About Their Own Papers
- 20Why developers are ditching GitHub for Codeberg and self-hosting alternatives
- 20Why older tech is sometimes safer from hackers
- 20The Coordinated Rename Is the Agent's Most Dangerous Refactor
- 20Custom home server built from spare parts
- 20A lattice with no mesh: sphere-tracing a signed distance field in raw WebGL2
- 20How AI Endpoints Change the Traditional API Flow
- 20orcarouter/GLM-5.3-Flash-Uncensored-FP8 (text-generation)
- 20WhyRep is now officially out! The workout logger that also analyzes your training.
- 20weblings: Compiling Rust to WASM from inside WASM
- 20My MCP Server Holds Two API Keys. Every Tool Call Runs in the Same Process as Both.
- 20Introducing Toolpak
- 20Federal vendor with $50M in contracts leaves portal broken for a month
- 20The Lion, The Witch, and the audacity of recruiters
- 20Microsoft MDASH Shows How Multi-Agent Security Systems Can Improve Vulnerability Discovery
- 20ratatop day 3: disks, statvfs, and my first unsafe block
- 20A Place for Everything: How I Track Work
- 20I wrote an API client for my water-cooled bed
- 20The GNU Emacs Architecture
- 20@coinbase/wallet-sdk — Coinbase Wallet JavaScript SDK
- 20A Speed Limit for Computers
- 20The Mysterious Syndrome Destroying Endurance Athletes
- 20theAuth Passwordless Login: Passkeys, Magic Links, OTP
- 20MNT Pocket Reform
- 20Unranked, systemd, crawls
- 20American Airlines mechanic Azriel “Al” Blackman has died
- 20RSS Feed Best Practices (2022)
- 20From Validating Code to Evaluating Behavior: Rethinking Testing for AI Agents
- 20How I made a Rust hot path 27x faster, and the AI fix I refused to merge
- 20Why My Angular 21 Upgrade Failed 👀
- 20WaveDigger: Dig into wireless signals to discover their physical locations
- 20My wife came home late every shift because of ultrasound paperwork, so I wrote her a program
- 20Should one parallelize an independent calls to a synchronous method using tasks or using threads?
- 20Rayfish - P2P VPN built on top of Iroh
- 202DWillNeverDie
- 20Yet another way to invoke functions without parentheses