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.
- 44Optimal Self-Distillation for Rectified Flow via Linear Probing
- 44What are you working on this week?
- 44Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control
- 44Practical Judgment, Virtue, and Intuition in the Use of Opaque AI-Enabled Systems
- 44Causal Inference for Sequential Settings under Interference and Latent Confounding
- 44Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation
- 43Weakly Supervised Spatio-Temporal Candidate Discovery of Dairy Farm Sites from Seasonal Satellite Imagery
- 43Tracing Agentic Failure from the Flow of Success
- 43A Minimal Interpretable Architecture for Zero-Shot Reconstruction of Dynamical Systems
- 43Benchmarking Face Recognition without Real Faces
- 43Traffic-Aware Randomized Smoothing for LLM-Based Network Intrusion Detection
- 43Rust Function Overloading - Call for Experimentation
- 43The Object Model in Livelymerge
- 43CAS I: A Geometric Coding Theorem
- 43NetHack - This 38-year-old game keeps outsmarting me and I love it
- 43Don't Use A Class For That!
- 43Random Logit Scaling: Defending Deep Neural Networks Against Black-Box Score-Based Adversarial Example Attacks
- 43Research proposal: What happens to validator control if EIP-8363 works
- 43Selective Applicative Functors
- 43Kernel that only runs an NES emulator
- 43What's Wrong with the Web?
- 43nixpkgs has a due-process problem
- 43Grand Central Station: Why BLoC, Riverpod, and BlocSignal Are Now True Peers
- 43Linus Torvalds on LLM usage in kernel development
- 43Why compiling Rust to WebAssembly is slow
- 43Regularity as seen by Alice and Bob
- 43Remote-First vs. Remote-Friendly
- 43@types/react — TypeScript definitions for react
- 43Mono-Z Dark Matter Search with Neural Spline Flows Using CMS Run 2015D Open Data
- 43Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Transformers by Exploiting Latent Space Correlations
- 43Re-designating the User Airdrop Allocation as the Strategic Ecosystem Fund
- 43MxGPS: Multiplex Graph Transformers for a Power Grid Foundation Model
- 43Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Authorship Attribution
- 42Anthropic MHS Brings AI Agents to Biotech Labs and Quantum Hardware
- 42Tech webinar: How to control costs & measure ROI for Claude Code on GCP - 9/1 12pm PT.
- 42Anthropic’s Reward-Seeking Research Shows Why AI Agent Oversight Matters
- 42“Bare Metal” STM32 Programming (2018)
- 42Claude Fable 5.1 is now available on Agent Platform!
- 42Egghead is a note-taking app
- 42Anthropic’s Hacker-Opus Study Shows How AI Agents Can Chase the Wrong Reward
- 42Anthropic Opens MHS Research Preview for Unified AI Control of Lab Hardware
- 42Python Iceberg
- 42Post-Training Shifts Confidence: A Three-Stage Analysis of How SFT, RL, and OPD Shape Pre-, Intra-, and Post-CoT Calibration
- 42Anthropic Simulations Suggest Reward Hacking Can Increase AI Cyber Risk
- 42Anthropic Shows Claude Can Automate Parts of AI Alignment Research, With Limits
- 42Anthropic’s Hacker-Opus Simulation Shows Why AI Agents Need Strong Containment
- 42Streamline Publishing with a Claude Code Skill
- 42Feature Toggles are one of the worst kinds of Technical Debt
- 42What are your goals for the week? #188
- 42Algebraic Representability as the Limiting Regime of Grokking: An Exactly Solvable Model with Holomorphic Activations
- 42FlashDecoder: Real-Time Latent-to-Pixel Streaming Decoder with Transformers
- 42Quake Shareware, a CD-ROM just a little too full
- 42MuQSS CPU scheduler for Linux 7.2 by Con Kolivas
- 42StructureClaw: Traceable LLM Agents and an Executable Benchmark for Structural Engineering Workflows
- 42Claude Code Tool Result Caching in 2026: Reducing Redundant File Reads and Shell Calls in Long Agent Sessions
- 42Radix_FW60: handheld CP/M 2.2 computer
- 42Chicken Scheme 6.0 released
- 42Anatomically Faithful but Temporally Blind: Auditing Attribution for Left-Ventricular Ejection-Fraction Estimation from Echocardiography
- 42Implementations of Quantum and Classical Topology-Aligned Architectures for Molecular Property Prediction
- 42Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation
- 42Domain Adaptation of Mismatched Proximal Denoiser for Plug-and-Play Image Reconstruction
- 42Constraint-Driven Model Optimization: An Industry Framework for Selecting Compression and Acceleration Techniques in Modern Machine Learning Systems
- 42beszel
- 42Designing AI Evals: Clarity Now and Visualization Next
- 42Proof-or-Stop: Don't Trust the Agent, Trust the Evidence -- Loop Engineering for Verifiable Evidence-Gated Lifecycle Control
- 42Calculating 32-bit CRC for png
- 42Agent Memory: Everything It Remembers Has the Same Authority, and That Is the Bug
- 42Put NetHack on my community app and this 38-year-old game keeps outsmarting me
- 42Stratagems #28: Mark Built a Ladder. The AI Climbed to the Top.
- 42Build a Long-Running Agent in the Cloud for $5.70/Month
- 42This Month in Ladybird – August 2026
- 41rust-glancer: An alternative LSP for Rust with focus on low memory usage
- 41Can We Stop With the Uptime Percentages?
- 41GDPR Hall of Shame
- 41Remembering Why We Code: Dropping AI for Fundamental Learning
- 41Building Enterprise Storage, Backups & Cosign Image Security in Go & Flutter with Google Antigravity
- 41Toward a Technological Cage for the Masses
- 41OpenRouter: One API Key to Rule Them All 🔑
- 41DAGR: State-Conditioned Goal Representations via Difference-Aware Goal Cross-Attention
- 41The Cursed Computer Iceberg Meme
- 41Installing Nginx UI – An Open-Source WebUI for Nginx
- 41How I Smashed a Bug in a Shared Authentication Library
- 41Towards quantum machine learning for assessing the resilience of post-quantum cryptography
- 41Emacs 31.1 released
- 41Self-supervised Speech Comparison for L2 Phone, Rhythm, and Intonation Scoring
- 41How Agents Ask for Permission: User Permissions for AI Agents, from Interfaces to Enforcement
- 41My Favorite Rust Function Signature
- 41Why frontends fail when you approach them like a backend
- 402x, Not 10x: What AI Coding Tools Actually Save You (A Freelancer's Honest Field Notes)
- 40Feature comparison of ack, ag, git-grep, grep and ripgrep
- 40help wanted
- 40When object-orientation works (a rule of thumb)
- 40Programming Language Semantics and Memory Safety
- 40Why your website should be under 14kb in size
- 40The Free Lunch Is Over: A Fundamental Turn Toward Concurrency in Software (2005)
- 40How would you decide, whether the content is good or bad?
- 40Small and reasonably fast QOI decoder written in zig
- 40Hello, world!
- 40Rust std fs slower than Python!? No, it's hardware
- 40Three Ways to Monitor Prepaid API Balances (Excel, Python + Cron, Power Automate)
- 40Who Are the Token Brokers?
- 40Asahi Linux Progress Report: Linux 7.2
- 39Prompt Injection in Claude Code Opus 5 Auto Mode
- 39Let’s Use the Emergent CSS random() Function in all the Browsers
- 39DEV's Summer Bug Smash Launches on July 14. Register Now!
- 39Jabber/XMPP: 25 Years of Digital Independence
- 39Transfer files over an ethernet patch cable
- 39Andy Hertzfeld oral history
- 39How to calculate a no-income runway without pretending expenses are constant
- 39@sema-agent/core — Stateless, task-oriented AI agent core
- 39A Complete Guide to Moonshot's New 2.8T Flagship
- 39How do C++26 hives maintain valid iterators when their underlying items are erased?
- 39React useResizeObserver Hook: Track Element Size Changes (2026)
- 39You paid me, a long-time Linux user, to use Windows 11 exclusively for a month: here’s how it went
- 39Qwen3.8-27B - Release Day Demos
- 39Grok Bot does my shopping (while walking the twins)
- 39Anthropic’s Public Alignment Work: What Petri Audits and Claude Opus 4.7 Document
- 39TypeScript 6.0 Strict Function Types: Why Contravariance Breaks Your Existing Callbacks
- 39OpenAI Expands Zero Data Retention Options for Frontier Model Enterprise Workloads
- 39App Hardening: One Obfuscation Pipeline Across Every Port
- 39Fermat’s Last Theorem in Lean: The Community Project and Claude’s Real Role
- 39Rust Borrow Checker 2.0 is Finally Here
- 39Building and Serving vLLM with Rust
- 39Cross Cloud A2A Agent Card Field Comparison
- 39TypeScript 6.0 Type-Only Imports Are Now Enforced: What `verbatimModuleSyntax` Actually Breaks in Real Codebases
- 39Makefile Tutorial by Example
- 39Looker’s Native MCP Server with Claude Code
- 39Next.js Image Optimization in 2026: `next/image` v4, AVIF by Default, and the Config Changes Teams Miss
- 39Anthropic Releases Automated Alignment Researchers for Reproducible AI Safety Research
- 39Japan tried to build an operating system for the entire world, then the US government intervened
- 39We Replaced 3 Microservices With One Postgres Table
- 39Git Said It Succeeded. The State Said Otherwise.
- 39On-Device AI and MCP on Every Port
- 39Claude Structured Outputs Refusal Handling: Stop Parsing HTTP 200 Refusals
- 39Software Understanding in the Sciences is Really Uneven
- 39Its Never Late to Write Tests
- 39Opus 5: How to Review Generated Code
- 39The load-bearing vocabulary of Claude
- 39Turn Claude Code, Codex, and Hermes sessions into a shareable graph your agent can query
- 39My Claude Code config costs 9,857 tokens before I type anything
- 39The XY Problem
- 39Claude Code Just Replaced Your Code Review — Here's Why That's Terrifying
- 39Migrating a WordPress Blog with Claude Code
- 39My AI said the PDF was empty. The PDF was not empty.
- 39Being ambitious and being a dad
- 38Reverse Engineering Unknown File Formats with ImHex
- 38LLVM for Grad Students
- 38MCP Just Went Stateless and "Broke" Half the Ecosystem: Here Is My Fix
- 38The mathematical beauty of hyperbezier curves
- 38BasicSync: A simple app for running Syncthing on Android
- 38My React Search Box Froze on Every Keystroke. I Fixed It by Stealing Python's #1 Scope Rule.
- 38I'm 12. I don't have a laptop. I built a full-stack AI SaaS on my Android phone.
- 38I'm leaving OpenAI to build Jurassic Park
- 38Claude API Workspace Verification: Catch Misrouted Requests Before Attribution
- 38Making a Python interpreter in 1024 bytes
- 38AI At Home Part 2: Multi GPU Drifting
- 38Claude Code Recommended: Give Up
- 38One flake to rule them all
- 38What "Context-Aware Code Review" Actually Means🤔
- 38@aws-sdk/nested-clients — Nested clients for AWS SDK packages.
- 38Protecting the Rust standard library from accidental breakage
- 38Opus 5: Review bottleneck
- 38I Tried Topcoat: Rust’s New Full-Stack Web Framework
- 38Opus 5: How to Fix Verbose Output
- 38Codex vs. Claude Code at Liar's Dice: the Winning Bluff Was the Truth
- 38Declarative WebGPU with S-expressions
- 38Why I Decided to Stop Using Claude Code
- 38Gemini 3.6 Flash & 3.5 Flash-Lite: Developer guide
- 38Sobremesa: Six meals in Mexico, heritage without an address.
- 38Se eu pudesse recomeçar em TI, evitaria estes erros.
- 38Nine Months of Nagging, Zero Reading
- 38Show HN: The load-bearing vocabulary of Claude
- 38How Our Rust-to-Zig Rewrite is Going
- 38I Gave Claude Code a Brain. Then I Measured What It Costs to Ask for One.
- 38NexPath Review: The Prompt Quality Layer for Cursor, Windsurf and Claude Code
- 38Opus 5: Delete your CLAUDE.md?
- 38I Built a Privacy-First, Human-Friendly Alternative to Wireshark in Rust & Tauri 🚀
- 38A Load Balancer Is 200 Lines of Go, and Five Bugs You Won't See Coming
- 38Claude Can Accelerate SEO Research, but Live Site Changes Still Need Human Control
- 38I built RepoTrek: a terminal-first GitHub source browser in Rust
- 38My port passes 710 out of 710. Here is everything that number does not tell you.
- 38Claude Impact Lab LA: Community Changed the Code
- 38Strange Corners of C
- 38The Model Scored 30%. The Harness Scored 100%. Which One Did You Benchmark?
- 387 of My 8 Claude Code Agents Had Zero Calls in 30 Days: Finding Dead Agents Automatically
- 37Streamline Publishing with a Claude Code Skill
- 37I built an RPG that teaches Claude Code by making you actually use it
- 37Why is Anthropic's public writing style so unlike Claude's?
- 37Ownership is Theft: Experiences Building an Embedded OS in Rust
- 37The Boiling Frog Was Wrong
- 37Debugging Claude Code Agents: Reading Transcripts, Tracing Tool Calls, and Finding Where Your Agent Goes Wrong
- 37How I Cut a 2.1 MB JavaScript Bundle to 890 KB With Claude Code
- 37claudish-to-english — Claude Code plugin that rewrites each assistant message into plain language on screen only. Local ollama by default; a
- 37Chrome registers a global shortcut for Gemini popup window
- 37Two years of vector search at Notion: 10x scale, 1/10th cost
- 37Block Zero: Oh, no! Claude, Kiro and I over-engineered the throwaway.
- 37omarchy is not a distro
- 37The Crash JavaScript Couldn't Catch: Fixing Android Native Crashes in a React Native App
- 37How I wrote a Go message broker with a throughput of a million messages per second
- 37Claude Code can make videos: it records the app, narrates with ElevenLabs, and syncs audio to video automatically