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
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
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
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
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
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
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
Hello, HellGatesPostmortem of a year-unsolved gate-level crackme that GPT-6 cracked in minutes
xutaxkamay recounts designing HellGates—a VHDL custom CPU with obfuscation, anti-tamper, and anti-debug that stumped humans and LLMs for a year—until GPT-6 solved it in under half an hour, then walks through what actually broke.
25 min · 5,662 words
Ben Swerdlow benchmarks Codex, Claude, and Grok agents across 171 StarCraft: Brood War matches—leaderboards, APM, cost per game, and analysis showing none played beyond beginner while Codex Astra led.
9 min · 2,151 words
I built non-autoregressive decision models with RL a year ago
Convai Innovations’ Nandakishor recounts building Laya—a ~33ms multilingual non-autoregressive decision engine with calibrated probabilities—via RLCD a year before frontier labs framed similar System One models as breakthroughs.
8 min · 1,852 words
TypeSafe's Jev AI Model in .NET: A Community SDK for Structured AI Output in C#
Laurent Kempé introduces TypeSafe’s Jev decision model and walks through a community .NET 11 / C# 15 SDK port so apps can get typed, structured decisions without brittle JSON parsing.
10 min · 2,298 wordsagent-assisted
How to Solve AI in Publishing with Three Easy(ish) Steps
Richard Pulfer proposes practical steps for the publishing industry to handle AI scandals and authorship concerns—focusing on disclosure, process, and standards rather than panic alone.
6 min · 1,475 words
How LLMs Actually Work: A Practical Guide for Product Managers
Abhishek Jaiswal explains tokens, transformers, attention, RAG, inference, and agents in practical PM language—so product leaders can make better build-vs-buy and quality decisions without becoming ML researchers.
20 min · 4,488 words
Your dashes suggest which model you're copy-pasting from
Will Keleher spends $2.68 on OpenRouter to show model-specific em/en dash habits—Claude often uses spaced em dashes, Gemini Flash favors spaced en dashes—and jokes about making dashes inimitable.
6 min · 1,301 words