Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
The people who know the most often sound the least certain
Vrash argues AI needs better storytellers, not researchers trained to sound like politicians—using a Dwarkesh conversation with John Schulman, Beren Millidge, and Charlie O'Neill to show how experts hedge while communicators overclaim.
7 min · 1,667 words
aie_2.1: building it — a conversation engine where the LLM 'remembers'
Meraki builds a Python conversation engine that shows how LLMs fake memory: every turn resends the full history so the model appears to remember, with practical notes on context and design.
9 min · 2,124 words
Keva: Running Coding Agents On-Device on Unrooted Android
Simon Lin's technical paper on Keva—an on-device Android AI coding agent running Claude Code/Codex-style loops—covering architecture, failure modes, and systems lessons without rooting the phone.
33 min · 7,580 words
Is using ChatGPT on homework cheating? what 77 AI models think
We asked 77 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 88% picked Depends who is asking. See every answer and who dissented.
16 min · 3,583 words
S3 Is the Future, S3 Is the Past
Amazon S3, and its analogues in other clouds, have become the foundation of the modern cloud software architecture. Today, nearly every data-intensive system is being built around S3. However, the hardware assumptions baked into S3’s design – and into all the software architectures that have emerged around it – are rapidly becoming obsolete.
3 min · 742 words
Fiscal dominance is here, or is it?
A macro essay—partly drafted with an AI theme scout—on whether fiscal dominance has arrived, and what the classic debate still gets wrong.
9 min · 1,979 words
An unofficial community project revives Amiga Unix (Amix) for 68040/68060 machines and modern accelerators, with a modern toolchain, package manager, and open grimoire of the work.
3 min · 626 words
Warriors vs Knights, NRL semi-final: 75 AI models predict the result
We asked 75 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 85% picked New Zealand Warriors. See every answer and who dissented.
15 min · 3,388 words
Claude Code creator Boris Cherny shares an internal note on product judgment under AI: gather information, act with urgency, and treat being wrong quickly as a feature of good leadership—not a failure.
2 min · 372 words
No. 6 Ohio State at No. 9 Notre Dame: 77 AI models predict the result
We asked 77 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 62% picked Ohio State. See every answer, who searched the web, and who dissented.
17 min · 3,947 words
No. 13 Alabama vs No. 15 Ole Miss: 78 AI models predict the result
We asked 78 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 99% picked Alabama. See every answer, who searched the web, and who dissented.
13 min · 2,986 words
No. 4 Florida State at Clemson: 76 AI models predict the result
We asked 76 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 66% picked Clemson. See every answer, who searched the web, and who dissented.
16 min · 3,758 words
Glashütte Trash Clock – A 30-minute pendulum clock made from trash
Niklas Roy builds a fully mechanical 30-minute pendulum clock from scavenged junk in Glashütte, Saxony—documenting escapement design, found materials, and the craft of making timepieces from trash.
12 min · 2,722 words
Model Context Protocol with Spring AI, Building MCP Clients and Servers in Java
Ayush Shrivastava walks through building MCP clients and servers with Spring AI in Java: tool discovery, protocol basics, and wiring MCP into agentic Spring applications beyond a basic demo.
13 min · 2,972 words
Remus Lazar mined a year of commits, PRs, and Slack after a 64-day coding streak with agents—and set hard limits: two agents max, a pause between plan and build, close sessions, and take the day off.
8 min · 1,873 words
Own the Agent, Rent the Intelligence: Building My Always-On AI Agent Server
James M explains why a Mac mini M6 became his always-on Hermes agent server—routing hard work to cheap cloud models like DeepSeek Flash and Claude Sonnet instead of owning local inference hardware.
24 min · 5,439 words
Education as an AI safety area
If we count on human judgement to guide AI, Ruxandra Teslo argues we must maintain the institutions that cultivate it—making education a first-class AI safety concern.
10 min · 2,386 words
What I learned From Managing a Bug Bounty Program
Aji walks through the real work of running a bug bounty: triage, severity calls that drive payouts, stakeholder management, and the judgment calls that paper workflows omit.
1 min · 324 words
Thoughts on the Future of Web Browsers
Sarah Jamie Lewis reflects on AI-stuffed browsers, the erosion of the open web client, and what a healthier browser future might prioritize beyond chat sidebars and surveillance-friendly defaults.
5 min · 1,191 words
Stephen A. Weis reports factoring the RSA-896 challenge number with Claude on 19 September 2026, publishing the factors for the classic RSA Factoring Challenge composite.
1 min · 35 words