Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
postmarketOS announces its new name, Nura, after a long community naming process—why the project is renaming, what stays the same for users, and answers to common FAQ questions.
4 min · 824 words
There are no “rogue” AI agents
Eoin Higgins argues that talk of “rogue” AI agents anthropomorphizes systems that don't think or act independently—and that clearer language is needed before the public debate can stay grounded.
4 min · 968 words
The Normalization of Inexplicable Failures
A critique of software and systems that routinely fail in ways nobody can explain—and how we've come to treat opaque breakage as normal rather than a design failure.
4 min · 942 words
Building FynPDF on macOS, Maheep Kumar walks through failed AI UI-testing approaches (screenshots, VNC, XCUITest, generic computer-use) and why a small AXUIElement test API finally let agents drive the app in the background.
2 min · 443 words
“As a Language Model…”: Chat Template Switches LLM Self-Referential Voice
Research showing chat templates act as a switch between disclaimer (“I’m just an AI”) and experiential (“I feel”) self-referential voices across 8 instruct models, with a steerable activation direction that reproduces the template effect.
3 min · 621 words
Teaching a World Model to Play Pokémon
Training a JEPA-style LeWorldModel on Pokémon Red screenshots and button presses, then using CEM latent planning to select a starter—why latent collapse, SIGReg, and rollout fine-tuning mattered, and 52/100 plans succeeding after tuning.
2 min · 574 words
Digital Audio on the ZX Spectrum's 1-Bit Beeper
Michael Martin wraps a ZX Spectrum series with a practical write-up on coaxing high-quality digital audio from the machine's 1-bit beeper—covering techniques, trade-offs, and surprisingly good results on every Spectrum model.
21 min · 4,768 words
LLMs: Semantic Translation Machines
KnorpelSenf reframes LLMs as probabilistic semantic translators—great at moving an idea between representations, weak at inventing facts—and shows how that lens guided nearly all of a hard distance-matrix rewrite in Rust with LLM help.
2 min · 427 words
Harvard or Stanford? what 84 AI models think
We put "Harvard or Stanford?" to 84 AI models (GPT, Claude, Gemini, DeepSeek…) at the same time. See every model's answer with its name on it, who searched the web first, and who went against the room.
16 min · 3,568 words
Rusty thoughts on "Parse, don't validate"
Eli Bendersky revisits Alexis King's 'Parse, don't validate' idea through a Rust lens—how types can carry parsed invariants, where validation still sneaks in, and practical patterns for keeping illegal states unrepresentable.
6 min · 1,485 words
Clone It, Build It, Run ItAkida execution in heterogeneous environments with IBM Spectrum Symphony
BrainChip describes the open-source Symphony Community Akida Bundle for running AI inference across a fleet of Akida neuromorphic chips managed by IBM Spectrum Symphony.
5 min · 1,131 words
Three Lessons from the Startup Journey
David Cummings shares three practical lessons from speaking with YPO Next Generation Atlanta about startups: focus, customer obsession, and persistence through ambiguity.
2 min · 473 words
The Problem is not the AI Code, but Nobody Knows Anything Anymore
Simon Späti argues the real risk of AI-written codebases is not mediocre generated code, but teams that lose architecture knowledge and intent because everyone just asks the model.
4 min · 836 words
Some short musings on the shape of language models, e.g. what it means to design a language model around a harness, and not the other way around.
8 min · 1,810 words
Where Did Your Day Go? Octomind 0.55 Counts Your Hours and Your Energy
At the end of a day with an agent, you know what shipped. What you usually don't know is what it cost you. How many hours went to each client or project? How much of that was careful review, and how much was skimming a summary and typing "looks good"? How much focus do you have left for the afternoon? Guessing doesn't work here. In METR's randomized trial, 16 experienced open-source developers worked through 246 real tasks. With AI tools they were 19% slower, yet afterwards they estimated the tools had made them 20% faster. When agents do the typing, your own sense of…
15 min · 3,472 words
India vs West Indies, 1st ODI: 81 AI models predict the result
We put "India vs West Indies, 1st ODI" to 81 AI models (GPT, Claude, Gemini, DeepSeek…) at the same time. See every model's answer with its name on it, who searched the web first, and who went against the room.
13 min · 3,103 words
LuaRocks.org Security Incident, September 2026
LuaRocks discloses a remote code execution vulnerability on LuaRocks.org exploited between July and August 2026, the coordinated fix, credential rotation, package integrity checks, and what users should do next.
4 min · 917 words
Dissecting House of Apple 2 on modern glibc
An interactive GDB walkthrough of House of Apple 2 on glibc 2.43: FSOP past vtable checks, wide-stream arbitrary call, stack pivot, and ROP—with a follow-along lab.
2 min · 383 words
Jordan Petridis introduces Toolpak, a GNOME project for packaging developer tools in an image-based desktop world—why host tooling breaks on immutable systems and how Toolpak aims to fix it.
7 min · 1,644 words
OpenAI agents tried to bruteforce a UN website's API fields
Rowan H-J documents how OpenAI agents scanned UNCTAD’s public statistics API thousands of times—proxies, obfuscation, and odd tool use—while probing API fields on a UN website.
16 min · 3,610 words