Claude Code vs OpenCode token overhead measured at the API boundary. Out-of-the-box baselines, instruction file weight, MCP schema tax, subagent multipliers, and cache-write behaviour.

My method for reading more

What xAI Grok Build CLI actually sends to xAI - a wire-level analysis (grok 0.2.93) - grok-build-cli-wire-analysis.md

I think from this blog you may misunderestimate how absolutely giddy I am about AI. I did hacking from 2007-2014, after that my whole career has been devoted to AI. I love the progress. I’m so excited for the new LLMs, self driving cars, video generation models, and coding agents. I set up a Linux box with opencode on my local GLM-5.2 last week and wow like just saying install tmux with the geohot configuration works; the Year of the Linux Desktop is finally here!

I have been interested in machine-assisted ways to do and teach mathematics from as far back as 1999, when I started coding several applets in Java 1.0, both for my complex analysis and linear alge…

Math.tanh, every CSS trig function, and the Web Audio compressor all route through the host libm, so the rounding of a cosine betrays the OS a browser actually …

Vinton Cerf, one of the creators of the protocols underlying the internet, will step down as Google's chief internet evangelist next week.

Send them $10,000. They send you $10,000. You

One simple vaccination may dramatically reduce the risk of dementia

We hold frontier models to a high bar, and for four months nothing beat Claude Opus. GPT-5.6 did. Here's the migration guide we wish we'd had.

This hard-hitting blogpost by Ken Murray, a retired Los Angeles family doctor, helped open up discussions about why doctors routinely administer treatments to dying patients that they would adamantly refuse for themselves. Years ago, Charlie, a highly respected orthopaedist and a mentor of mine, found a lump in his stomach. He had a surgeon explore

Consumption rose another 10% while restrictions on most new grid connections remained around Dublin

Around 2000 I took an AI course at the University of Guelph. I don't think I learned too much. We didn't talk about neural networks, as far as I can remember. My end of term project was, I think, a pathfinding algorithm wearing an AI costume. There were certainly no discussions of transformers. No CUDA. No PyTorch. None of that existed.
But what I remember doing a lot of was coding in Lisp - a lot of Lisp in the dark University of Guelph CIS lab.

A bunch of reasons to write code in 2026

If an undergraduate program's graduates don't earn more than workers who never went to college, that program could be cut off from federal student loans. But is a degree just about making more money?

A visualization tool that replays coding-agent sessions on a 3D map of your codebase. - cosmtrek/mindwalk

The domestic worker, who entered the household at the age of seven and never received wages or vacations, is set to be compensated by her employers

Learn the Odin Programming Language and demystify low-level programming

Virginia Tech scientists at the Fralin Biomedical Research Institute show that resistance training outperforms endurance exercise in improving insulin sensitivity in obesity and Type 2 diabetes models.

We

Two developments are unfolding at once: artificial intelligence systems have begun to produce genuine research-level mathematics, and the United States is weakening the pipeline that produces humans capable of understanding what such systems are doing. This essay argues that, taken together, these developments amount to a strategic error. Mathematical capacity, which is the trained ability to verify, interpret, and challenge mathematical reasoning, is not a byproduct of theorem production but a form of infrastructure, built over generations by institutions that cannot be reconstituted on demand. Drawing on the May 2026 AI disproof of a longstanding Erdős conjecture on the planar unit distance problem and on recent disruptions to federal support for the mathematical sciences, the essay makes the case for treating mathematical capacity as a strategic asset on a par with semiconductor capability. It further proposes, among other measures, that AI systems performing consequential reasoning be required to expose their decision-critical claims in formal, machine-checkable form, converting part of AI reasoning from opaque persuasion into auditable structure.

ESP32-P4 + C5, AMOLED touchscreen, wireless, sensors and real I/O in your pocket. You write the code — it becomes whatever you need. For makers, pentesters and geeks.