Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
Who wins Super Bowl LXI? 85 AI models predict the result
We asked 85 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 49% picked Chiefs. See every answer, who searched the web, and who dissented.
10 min · 2,394 words
PlanetScale Released Text Search and We Have a Lot to Say (Part I)
Two BM25 optimizations and benchmark configuration changes inspired by PlanetScale's TIN benchmarks make ParadeDB's text search faster without changing its document identifiers.
14 min · 3,188 words
Context management is an underrated habit
How you manage context in a Claude Code session has a direct effect on both your token bill and the quality of what you get back. Do it well and you spend less for better work. An efficient session gives Claude the context it needs to finish the job while removing context that has stopped being useful. That means starting with a lean setup, keeping investigations focused, and deliberately deciding when to continue, compact, or start again. Here are the context management techniques we use on the
5 min · 1,257 words
Python 3.15 ships with a new profiler. It is called Tachyon, it lives in the standard library as the profiling.sampling module, and unlike cProfile it is a sampling profiler rather than a tracing one. I now have a set of hands-on workshops for it, which you can find at github.com/GrahamDumpleton/tachyon-workshops or on the workshops page of this site, and they have reached the point where I am happy for other people to do them. That said, they were not written for other people in the first place. They were written so I could learn Tachyon myself, and the reason I wanted...
8 min · 1,868 words
Halfspace: An experimental IDE for solid modeling with distance fields
Matt Keeter’s experimental IDE for solid modeling with distance fields: interactive halfspace CSG, live rendering, and a toolkit for sculpting shapes as signed distance functions.
6 min · 1,448 words
Document Review With Unsiloed and TypeSafe Jev
Unsiloed AI and TypeSafe’s Jev show a document-review pipeline that pairs extraction with schema-validated checks so OCR-correct but semantically wrong values (like an extra zero) are caught before they flow downstream.
6 min · 1,330 words
Equality Saturation: An “Incomplete” Project
Max Willsey revisits equality saturation five years after the egg paper, surveying egglog, Slotted, Colored and Versioned E-Graphs, Cranelift's aegraphs and MLIR integrations, and arguing that giving up completeness has been a strength that enables flexibility, control and a growing research community.
8 min · 1,798 words
GitHub repository landing pages now show an accessibility tab, if provided
Eric Bailey describes his last official contribution at GitHub: repository landing pages now surface an ACCESSIBILITY.md accessibility statement in the same tab strip as the README, license, and security files, with tips on what to put in one and why it matters.
2 min · 408 words
The complement of true is true, except when it's false
Matthew Taylor digs into a C++26 bitmask-enum proposal and the surprising boolean-algebra edge cases around complements, truthiness, and what ‘all bits set’ really means in practice.
15 min · 3,463 words
More like SC-Forth-thousand, am I right?
Porting a Forth environment to the Sega SG-1000 / “Soggy” for low-level hardware tinkering, with notes on the bring-up and what works so far.
20 min · 4,584 words
How we built long-term memory for Alyx: why we chose a file over a knowledge graph
Arize engineer Priyan Jindal recounts building long-term memory for the Alyx AI engineering agent: after weeks on vectors and knowledge graphs, they shipped one structured 8,000-character text file per user/space, read on every request—and how they update, compact, and test it.
23 min · 5,269 words
Intelligent If-Statements: Jev vs. LLMsWhat if your if-statements could think?
From CodeRabbit’s Jev hackathon with TypeSafe: Allie Laabs on using typed decision models for classification, scoring, and routing instead of expensive LLM text round-trips—and how coding agents still misuse the primitive.
8 min · 1,779 words
Building Guardian Pocket: The Local Health Agent You Actually Own
This is Guardian Pocket. It's the world's first local health agent where YOU own the data end to end.
5 min · 1,261 words
Various Projects Independently Find Hidden SDR Capabilities in ESP32 Microcontrollers
ESPARGOS and independent projects uncover undocumented ESP32 IQ/baseband access enabling 2.2–2.7 GHz (and C5 5 GHz) SDR use—spectrum snapshots today, with ESP32-S31 Ethernet streaming and FPGA USB paths toward continuous demod.
3 min · 575 words
The Placeholder Is DeadAn honest estimate beats fake precision
VEXIS shipped a pricing tool that literally labeled unfinished rates as placeholders, then replaced them with negotiated card rates—and caught a stale summary label the green tests missed.
2 min · 444 words
Why we built the fastest robust TTS model
Gradium's latest streaming TTS hits ~50ms time-to-first-audio while improving naturalness and hard cases like phone numbers—freeing latency budget for LLM turns and barge-in in voice agents.
2 min · 431 words
zenkai: The App Launcher I Wrote Because I Wanted Something Fast and Beautiful
Dayvster builds zenkai, a Zig + Qt6 cross-platform app launcher with ~140ms startup (sometimes ~20ms), 65+ themes, Lua plugins, and a sandbox—written as a hobby performance deep dive.
2 min · 571 words
Earendil's experimental Pi Durable harness brings Pi's minimalism to long-running agents: crash-safe tasks, multi-conversation concurrency, pluggable extensions, compaction, durable documents, and multiplayer steering on JS runtimes.
5 min · 1,053 words
India vs West Indies, 3rd ODI: 79 AI models predict the result
We asked 79 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 96% picked India. See every answer, who searched the web, and who dissented.
10 min · 2,281 words
Being asked to sanitise Wikipedia entries
Longtime Wikipedia editor Ruben Schade describes getting paid and unpaid requests to scrub contentious material from articles—and draws a hard line against editing for hire or removing valid citations.
1 min · 224 words