Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
Which job will AI replace first? what 85 AI models think
We put "Which job will AI replace first?" to 85 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 · 3,016 words
Who wins the 2026 World Series? 83 AI models predict the result
We put "Who wins the 2026 World Series?" to 83 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 · 2,999 words
Free the models: Harness design at the frontierWhy Replit Agent lets the core loop pick subagent tier, effort, and specialists—and beats rigid routers on cost/score
Replit's AI team argues model routers are always weaker than the models they choose for. Their harness lets GPT-6 Astra decide effort and delegation; on DeepSWE and Terminal-Bench, Replit Agent is Pareto-efficient versus Astra alone and a sidekick architecture.
2 min · 558 words
India vs West Indies, 2nd ODI: 81 AI models predict the result
We put "India vs West Indies, 2nd 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 · 3,016 words
Osborne Saldanha’s practical playbook from running personal agents for trading, health, and investing: isolate one profile per job, separate skills/tools/engines, ground truth outside the model, and gate expensive LLM calls behind cheap logic.
3 min · 582 wordsagent-assisted
Making np.searchsorted up to 25× Faster in NumPy 2.5
Alejandro Candioti explains how NumPy 2.5 makes np.searchsorted up to 25 times faster by batching many binary searches so their independent memory accesses overlap, starting from a vectorized Python prototype that beat NumPy 2.4's native code, and discusses cache-friendly layouts like Eytzinger as a future direction.
12 min · 2,861 words
Shahid Hussain recounts a 15-year search for Salvage, a band whose two professionally produced tracks, Electric and Searchlights, he heard in 2011 before the band seemingly vanished. Generic names, a lost CD and thin online traces made it hard, until persistent digging finally connected him with the producer and musicians behind the songs.
10 min · 2,355 words
Faster streaming HTML with batches and aggregates
Anders Murphy explores emergent properties of server-rendered streaming HTML over SSE with Datastar: bounding work with ticks, batching and barriers, Brotli or Zstandard streaming compression, querying the database every tick, a simple hiccup interpreter and cache thrash, with his hyperlith demo serving about 1000 concurrent users at 10 FPS on a 2 vCore VPS.
7 min · 1,610 words
5x faster Edge Functions: How we replaced v8 isolates with Firecracker MicroVMs
About a billion Edge Functions run on Netlify every day — Sunweb personalizing pages, LotoQuébec routing traffic on a cookie check, and hundreds of thousands of other sites doing everything from personalization to routing to auth. All of it runs on a full JavaScript runtime that scales with our customers’ traffic.
8 min · 1,844 words
Yet Another AI Security OSS Externality
Holden Karau recounts working AI-lab vulnerability reports during Apache Spark releases, and why AI security often externalizes cost onto open-source maintainers who lack resources to verify opaque claims.
9 min · 2,135 words
Hugging Face’s Tarek Ziadé explains Serge, a CI agent that finds Transformers failures, reproduces them on GPUs, writes patches, verifies them, and opens PRs—29 merges in ~80 days.
9 min · 2,070 words
Floppy Emu Hardware Failure Analysis Results
Steve digs through years of Floppy Emu QA failures and returns: clock crystals dominate the failure table, with CPLDs, programming misses, and soldering filling out a detailed hardware autopsy.
5 min · 1,165 words
You Said No MCP!Why Pi (pi.dev) brought MCP into the core after years of saying no
Earendil explains why Pi now ships MCP in core: MCP matured, Codemode/JavaScript sandbox composition made it useful, and embracing modern MCP helps shape better tool patterns for small harnesses.
5 min · 1,048 words
Backblaze Drive Stats for Q2 2026
Backblaze’s Q2 2026 Drive Stats: 354,415 drives at 1.73% quarterly AFR, lifetime AFR 1.41%, plus a clear CMR vs SMR primer as 20TB+ drives become a larger share of the fleet.
11 min · 2,548 words
macOS Golden Gate Is a Buggy Mess
SquareOrbits argues Apple's macOS Golden Gate release echoes Snow Leopard's stability pitch but ships with serious bugs—including a Colours eyedropper hang that force-restarts the system—and catalogs the breakage from a working-Mac perspective.
4 min · 914 words
Mass Fraction: a love letter to Deuteros, in sixteen colours
Arda Karaduman launches Mass Fraction, a hard-SF space-industry strategy game at 640×512 in sixteen colours—mapping Deuteros and Millennium 2.2 into a Godot sim of Lid debris, named crews with dose ledgers, and indifferent Harrow machines.
5 min · 1,252 wordsagent-assisted
An update on Angular’s TypeScript 7-powered Compiler
The Angular team explains ngp, a hybrid preprocessor that rewrites parts of the Angular compiler in Rust with Oxc, decoupling transforms from TypeScript to prepare for TypeScript 7 and native tooling.
6 min · 1,431 words
What is the biggest unsolved problem in science? what 84 AI models think
We put "What is the biggest unsolved problem in science?" 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.
19 min · 4,300 words
Why refactoring made our biggest file biggerCode entropy, measured, and the ratchet that stops it
Image Horse's AppShell grew from 3,250 to 3,806 lines during a month of intentional extraction. Chris Lane Jones explains measured line-count ratchets, why warnings failed, and why entropy is whack-a-mole you don't win—but can make visible.
5 min · 1,168 words
How Pew Research Center is – and is not – using AI in our work
Pew Research Center outlines internal AI guidelines: surveys stay human-answered, disclosure rules for production use, and careful experimentation while keeping research people-centered.
2 min · 542 words