Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
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
Language Models for Text Classification: From Bag-of-Words to JevA visual guide to bag-of-words, RNNs, CNNs, transformers, Jev-like APIs, and calibration
Sebastian Raschka walks from classic bag-of-words classifiers through RNNs, CNNs, and transformers to TypeSafe AI's Jev—explaining APIs, IMDb benchmarks, calibration, and why decision models matter for agent harnesses.
5 min · 1,076 words
Software Goldilocks: the market for software is expanding but is the System of Record dead?
Sam Gerstenzang argues AI expands SaaS spend while splitting value into small opinionated point tools and large full-service “does the work” products—squeezing classic mid-market systems of record from both sides.
2 min · 520 words
Responsible Release of AI-Generated Mathematics
The Advisory Group on Mathematics and AI (Sep 29, 2026) recommends how frontier labs should release AI-generated math results: deposit promptly, cite related work, formalize where possible, disclose prompts and costs, and fund community-led human understanding.
2 min · 559 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
Bryan Caplan vs Effective Altruism
Walter Veit challenges Bryan Caplan's recent criticism of effective altruism, arguing the debate should turn on arguments, reasons, and evidence rather than dismissive pseudo-philosophy.
6 min · 1,271 words
OpenAI announces dots, always-on agents designed to stay with users across tasks—covering what they do, how they differ from chat sessions, and how to get started.
6 min · 1,385 words
You Are No Longer Invited to DinnerThe death of the American host
Derek Thompson traces a half-century collapse in Americans hosting friends at home—from 42% monthly in 1975 to 12% in 2026—and weighs harried dual-earner households, screens, and other explanations for the great disinvitation.
10 min · 2,257 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
Generation Got Cheaper Again. Verification Didn't.
O'Side Systems on the growing gap between cheap AI code generation and slow human verification: cost per accepted change, review queues, and where engineering leaders should invest next.
5 min · 1,218 words
Ben Sixsmith argues that strange times make it necessary to take strange people seriously—from rocket pioneer Jack Parsons to today's eccentric AI-and-tech scenes—and why the future may belong to the weird.
3 min · 764 words
Your car is collecting more data about you than you thinkNortheastern researchers tested 21 vehicles and companion apps for third-party data sharing
Northeastern cybersecurity researchers, with Consumer Reports, found connected cars and OEM apps sending VINs, location, and emails to advertising and analytics third parties—and call for clearer opt-in defaults.
2 min · 414 words
OpenClaw Enterprise - The Open Agent Platform
The OpenClaw Foundation announces OpenClaw Enterprise (OCE): an open-source, vendor-neutral control plane for persistent agents with multi-tenancy, hard security boundaries, and governance—developed with Red Hat and NVIDIA after originating at OpenAI.
3 min · 592 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
How to Build a Reliable AI Assistant with the Claude API
A freeCodeCamp tutorial building ShopHelper with the Claude API: conversation history, tools, multi-block responses, workflow patterns, and evaluating whether prompt changes actually help.
9 min · 2,132 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
Building a certificate authority for the whole Internet
Cloudflare announces intent to become a public CA: root-program applications, a GlobalSign root acquisition for device reach, ACME-first free issuance, fail-small design, and plans for Merkle Tree Certificates in 2027.
8 min · 1,814 words