Every analyzed article

Obfuscation (Part II): Diamond iO (vitalik.eth.limo)

Where USB Memory Sticks are Born « bunnie's blog (bunniestudios.com)

The mean means nothing (fzakaria.com)

GitHub - mokshablr/gander: Take a gander at any file. Offline, zero-permission Android viewer for PDF, Word, Excel, PowerPoint, photos, video, audio, Markdown and code. (github.com)

Change Log | DeepSeek API Docs (api-docs.deepseek.com)

Stronger with every update: How we’re making Chrome and the web safer in the AI Era (blog.google)

The Session You Cannot Take With You | EARENDIL (earendil.com)

8389219: Implement JEP 401: Value Objects (Preview) by MrSimms · Pull Request #31120 · openjdk/jdk (github.com)

Speaking to AI Agents like Cavemen Saves 65% of Tokens. We Test. (blog.jetbrains.com)

This Viral Data Center Sounds Like Satan’s Buzzsaw (gizmodo.com)

The AI Aesthetic (blog.jim-nielsen.com)

Port Zero — stable domains for your local dev ports (portzero.net)

Bad Apple!! but it's traceroute (jssfr.de)

GitHub - AminBlg/SimpleEnglish: Agent skill: make LLMs write docs in ASD-STE100 Simplified Technical English — no AI slop (github.com)

GitHub - MemoireMorte/Memo-1: A simple 6502 based computer (github.com)

We don't need no stinkin' tensor library (phulin.me)

We don't need no stinkin' tensor library (phulin.me)

What Would It Mean to See a New Color? (newyorker.com)

Postgres Queues Actually Scale (dbos.dev)

What a Distilled Model Inherits From Its Teacher (ctgt.ai)

Supapool: Real Supabase for parallel coding agents (supapool.io)

GitHub - experientiallabs/world-model-optimizer: Build continually improving models on your agent traces by distilling frontier open models (github.com)

2x, not 10x: coding with LLMs in 2026 (obryant.dev)

Statement on behalf of UEFA and its 55 national associations (uefa.com)

So you want to use plants to reduce CO₂ (dynomight.net)

Tally by JieGou — does the report you're about to send match your data? (tally.jiegou.ai)

GitHub - yashmahajan10/llm-differential-privacy-gateway: Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a formal guarantee no individual's record can leak even if the agent is adversarial - enforcement lives in trusted code below the model, validated by a runnable attack gallery. (github.com)

Postgres Queues Actually Scale (dbos.dev)

CodePen 2.0 (chriscoyier.net)

How to Mount a Balcony Awning (solar.lowtechmagazine.com)