Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
How I changed teaching after AI managed to do all my homework assignments
CMU-style software engineering instructor Christian Kästner redesigned assessments after AI agents could finish take-home work: oral exams, demos, and tradeoffs against evidence-based pedagogy.
16 min · 3,576 words
AWS’s Matt Wood argues AI agents change ops from “is it broken?” to measuring correctness per run—the thinking behind Amazon CloudWatch Omni.
5 min · 1,214 words
How to serve trillions of tokens for trillion-parameter coding agents
Modal explains how it serves coding-agent inference at extreme scale—performance and efficiency techniques for trillion-parameter models generating trillions of tokens, written for teams facing the same workload.
30 min · 6,972 words
Electric Capital open-sources Quest, a safety-first AI harness that keeps sensitive data inside your perimeter unless a user explicitly approves outbound access—Apache 2.0 on GitHub.
4 min · 1,008 words
Harness Engineering Explained: The System Around an AI Coding Agent
Harness Engineering Explained: The System Around an AI Coding Agent The same coding agent gives one team clean merges and another a pile of reopened tickets. The difference is rarely the model. It's the six parts around it, checked one ticket at a time.
11 min · 2,490 words
arXiv receives multiyear investment to support independent nonprofit launch
arXiv announces $17.2M in multiyear philanthropic commitments from the Simons Foundation International, XTX Markets, and the Siegel Family Endowment as it launches as an independent nonprofit.
4 min · 825 words
Towards Universal Post-Training for Robotics
Perry Dong and Chelsea Finn on why robotics RL differs from LLM RL, what EXPO-FT gets right and wrong, and what a universal post-training recipe for real-world robots still needs.
15 min · 3,484 words
I Got Tired of Vibe Coding, So I Rebuilt the SDLC as Twelve Agent Skills
Zeeshan Hanif open-sources a twelve-skill agent kit that turns vibe coding into a disciplined pipeline—from requirements interview to deployed, verified software with decisions traced on disk.
19 min · 4,397 words
Michael Heap on why leaders asking for “reasonable explanations” can stall change: good stories aren’t fixes, process theater replaces outcomes, and trust depends on asking the right question instead of drowning in details.
4 min · 845 words
Evading Machine Learning Based Detections
Companion post to an x33fcon talk on packer/loader architecture and how machine-learning-based detections work—plus practical ML-evasion techniques and RustPack 1.7 features that aim to bypass those detectors by default.
13 min · 2,880 words
Flavio Copes explains Ponytail, a plugin that stops coding agents from over-engineering: how it works, how to install it in ChatGPT, Codex, and Claude Code, intensity settings, and a practical workflow for keeping agent-built features small.
10 min · 2,212 words
An essay arguing that LLM tokens are heading toward electricity-like cheapness within a decade—covering GPUs, models, inference engines, MoE, local vs hosted AI—and what Jevons-paradox demand and investor returns look like when inference is abundant.
14 min · 3,198 words
What is the most useless college major? what 84 AI models think
We asked 84 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 17% picked General Studies. See every answer and who dissented.
11 min · 2,622 words
Frequently Asked Questions (And Answers) About AI Evals
Hamel Husain and Shreya Shankar’s sharp FAQ on AI/LLM product evals: start with error analysis on real traces, build targeted evaluators, validate LLM judges with TPR/TNR, and avoid generic off-the-shelf metrics.
74 min · 17,016 words
Semantic memory or just Markdown?
Laravel Boost tried embeddings and semantic search for project rules, then deleted them: a generated Markdown index plus grep proved simpler and more reliable for teaching agents existing conventions.
7 min · 1,562 words
The darker side of being a doctor
Surgeon Dr Eric Levi writes about the hidden costs of medical training and practice—burnout, identity fusion with the role, and the quieter mental-health strains that resilience culture often papers over.
8 min · 1,797 words
SDF vs. MSDF vs. Slug: GPU Text Rendering
Chris Hanson compares SDF, MSDF, Slug, texture atlases, and Rive for GPU text: how signed-distance fields trade sharpness, memory, and shader cost when you draw outlines yourself.
15 min · 3,398 words
mantle.nes breakdown blog part 1
Drmelon walks through building mantle.nes—a multi-month NES demake/fangame of a Deltarune Chapter 3 sequence—covering constraints, techniques, and why the project took shape.
16 min · 3,755 words
Honest About Uncertainty: I Tried to Rebuild Jev’s RLCD From a Blog Post
Anthony Maio reverse-engineers a plausible RLCD training loop for decision-only models from TypeSafe’s Jev blog post, then trains and evaluates a small Qwen3-0.6B checkpoint—with code and ablations.
19 min · 4,310 words
LA Metro has some of the slowest escalators on Earth
If you’ve ridden an escalator in Hong Kong or Singapore, the climb out of an LA Metro station can feel painfully slow. It’s really not just Metro though, American transit escalators generally operate under a much lower speed limit than those in much of the world. Why? Well honestly we don’t have the whole answer, but we did look at the rules governing escalators in 139 cities across 58 countries and came to some interesting conclusions. One of them is that LA Metro’s specified speed is below the maximum allowed in every single city on our list. That doesn’t mean we…
4 min · 815 words