Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
The Go team introduces experimental architecture-specific SIMD APIs in Go 1.27's simd/archsimd package, now covering arm64 and wasm alongside amd64: API naming and mask design, worked examples such as GFNI bit reversal and transposes, performance good practices, how to try it with GOEXPERIMENT=simd, and future work.
11 min · 2,476 words
Andrew Plotkin (Zarf) dissects a wild-pointer memory-corruption bug in Infocom's Infidel, nearly invisible in play, that he spotted with a memory-level debugger while working on Visible Zorker, down to the ZIL code and Z-machine details.
9 min · 2,179 words
Automating my 35mm film scanning pipelineA story about replacing a creative workflow and focusing on another.
Shan Hannadige describes automating the tedious parts of scanning 35mm film from a Canon AE-1P, building a pipeline and a site to present the results, and what it means to delegate one creative workflow to focus on another.
5 min · 1,257 words
One vector is too few. One per token is too many.
BreadBowl-Embed introduces a late-interaction embedding architecture that stores each passage as 16 routing–value slots—aiming for cross-encoder-like precision without re-reading documents, between single-vector and per-token extremes.
15 min · 3,524 words
Klassik Revives the KDE 3 Desktop on Modern Plasma 6
Klassik is a new open-source project that brings the classic KDE 3 desktop experience back to life on top of the modern KDE Plasma 6 stack.
2 min · 373 words
I got targeted: Trying to get your credentials via a git post-checkout hook
A security incident write-up: someone tried to run arbitrary code on a developer laptop via a malicious git post-checkout hook, likely aiming at GitHub and client access—what happened, how it was spotted, and practical defenses.
2 min · 503 words
How Futhark’s compiler keeps sparse Jacobian graph-colouring work efficient on the CPU—why not every data-parallel kernel belongs on the GPU, and what that means for the language’s CPU backend.
7 min · 1,610 words
One month coding with GLM 5.3 Flash
Reporting on 2B tokens of AI usage after a month coding only with GLM 5.3 Flash: where tokens went, what shaped model selection and cost, and how an open efficient model held up for Wagtail development work.
3 min · 735 words
The forgetful CPU (Linux on M4)
A detailed write-up of first-booting Linux on an M4 Mac mini, covering CPU quirks, bring-up details, and the hardware surprises along the way.
7 min · 1,650 words
SequenceHash: multihashing for the rest of us
Multihashing is one of those cryptographic tasks that’s easy not to think about too much. This is unfortunate, because multihashing is a common stumbling point when cryptographers try to use hashes.
13 min · 2,942 words
Spring AI Modular RAG and TypeSafe Jev: Retrieve More, Keep Only What Answers
Christian Tzolov walks through Spring AI modular RAG plus TypeSafe Jev: rewrite/expand the query before retrieval, then keep only chunks that actually answer—contrasting naive QuestionAnswerAdvisor RAG with a live demo pipeline.
6 min · 1,487 words
I let an AI agent run my side project's growth loop: intent.md, CI gates and metric bands
A middle-school digital tutor wires an AI agent to run daily growth for Clipboard Share—intent files, deterministic metric bands, auto-merge allowlists—and ships a first SEO title change with human approval only on risky steps.
6 min · 1,356 wordsagent-assisted
Building reliable (and fast) directory syncWhy Firezone skipped SCIM and built a hybrid pull + change-notification engine
Firezone explains directory sync without SCIM: pull-based reconciliation, provider change notifications, epoch checkpointing, and defensive handling of nested groups so identity updates stay fast and complete.
12 min · 2,670 words
Meta's Muse is fantastic for web scraping
I haven’t found much use for the personal assistant part of Muse. People on X (Twitter) keep using these assistants to order DoorDash or something. I order DoorDash like five times a year, so that’s not going to speed anything up for me. I also don’t get many emails, and managing my appointments is easy enough already.
2 min · 573 words
HITL gates for agent mutationsVerify mutations after tool calls so agents cannot declare early victory
Human-in-the-loop risk gates for refunds, inventory, and spend: classify mutations, issue system approval ids, and verify with a second read before user-facing success copy.
2 min · 501 words
Deleting RAG from our web agent made it 2.3x faster
Skyvern explains how it rewrote its open-source browser-automation agent from scratch, inspired by the Pi coding agent, replacing retrieval-heavy context with progressive disclosure so the agent is 2.3x faster and scores 90.5% on the Odysseys web-agent benchmark.
5 min · 1,105 words
turbopuffer is pushing the frontier of search. To do that, we have to fundamentally redesign our storage architecture so the vector index is no longer primary.
6 min · 1,334 words
Archiving The World's Oldest Webcam Feed
Hackaday covers Fog-Bank, Justin Earl’s multi-network scraper that preserves FogCam—the San Francisco State University webcam that has been uploading images since 1994—now holding hundreds of thousands of frames.
1 min · 249 words
OxCaml - Stack Allocations and Locality
The motivation behind OxCaml is to make OCaml a great language for performance engineering, with the eventual goal being to upstream these language extensions to vanilla OCaml (OxCaml](https://oxcaml.org/)). OxCaml maintains backwards compatibility with OCaml, which implies that every OCaml program is a valid OxCaml program. The language extensions range from additions to the type system that rule out data races, to control over allocations that reduces garbage collection pressure, to management
7 min · 1,697 words
The bat and ball problem: what 84 AI models think
We asked 84 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. The answer was 5 cents; 81 got it right. See every answer and who dissented.
10 min · 2,214 words