Software Factories Are Here and Engineers Are Now Operators
Factory just said the quiet part out loud. Engineers don't write software anymore. They build the factories that write the software. Here is what that actually means.
#engineering
24 posts
→
I Built a Skill That Turns Claude Into a Project Manager
A single command that decomposes a plan, spins up parallel sub-agents in isolated git worktrees, runs QA, tracks costs, and delivers a tabbed HTML report. Here is how /buildthis works, why I built it, and how to install it.
aiautomationengineeringguide
→
Five Steps of AI Adoption and Why Most Teams Are Stuck on Step One
Boris Cherny published a framework for AI adoption that maps the journey from gated access to thousands of autonomous agents. Most engineering teams think they are further along than they are. Here is how to tell where you actually stand.
aiautomationenterpriseengineeringguide
→
The Meter on the Mind
For most of computing history, thinking was free. In 2026 it got a price tag. We metered cognition, and every metered utility eventually gets gamed.
aieconomicsengineeringtokensproductivity
→
Token Maxxing Is a Fad. The Best Engineers Use the Least.
Meta ranked 85,000 staff by token use. Amazon and Uber followed, then all scrapped the leaderboards. The best engineers code with intent, not volume.
aiengineeringproductivitytokenmaxxingcoding
→
43% of AI-Generated Code Breaks in Production
Lightrun surveyed 200 SRE and DevOps leaders: 43% of AI code needs manual debugging, 0% are very confident, and Amazon lost 6.3M orders to it.
aiengineeringvibe-codingdeveloper-toolsobservability
→
Claude Opus 4.7 Tops the Arena. Developers Disagree.
Opus 4.7 took #1 on Arena, SWE-bench jumped 7, vision tripled. But MRCR fell 46 points and the tokenizer quietly inflated costs. What benchmarks miss.
aibenchmarksanthropicengineeringinfrastructure
→
Darkbloom: Private AI Inference on Idle Macs
Eigen Labs turns idle Macs into AI compute nodes where the owner cannot see your prompts. How the private-inference network works, and what breaks.
aiinfrastructuresecuritydistributed-systemsengineering
→
OpenAI Just Built a Hacker. Then Gave It to the Good Guys.
GPT-5.4-Cyber finds bugs and chains exploits. OpenAI gives it to thousands of vetted defenders; Anthropic locked its version to 40 orgs. Two bets.
securityaiengineeringinfrastructureopen-source
→
IPv8 Explained: The IETF Draft to Replace IPv4/IPv6
A new IETF draft proposes IPv8: 64-bit addresses, IPv4 as a subset, 8 services in one Zone Server. What is genuinely novel, and what is fantasy.
networkingengineeringsecurityinfrastructureopen-source
→
Spark 2.0 Streams 100M Gaussian Splats to Your Browser
World Labs open-sourced Spark 2.0: a streaming Gaussian Splatting engine rendering 100M+ splat worlds in any browser via Three.js and WebGL2.
ai3dopen-sourcewebengineeringdeveloper-tools
→
Living Human Neurons Are Now Choosing the Words an AI Speaks
Cortical Labs grew 200K neurons on a chip, taught them to play Doom, then wired them into an LLM. The neurons now override token selection in real time.
aiengineeringopen-sourcesecurityproductivity
→
AI Is a Multiplier, Not a Magic Bullet: DORA 2025
DORA surveyed 5,000 devs. AI makes good teams great and broken teams worse. Here is the 7-capability playbook that separates the two.
aiengineeringdevopsdeveloper-toolsproductivity
→
Why 20% of Companies Capture 74% of AI's Value
PwC surveyed 1,217 execs across 25 sectors. The top 20% take 74% of AI value, and the gap is not budget. It is strategy. Here is what they do.
aistrategyengineeringleadershipdata
→
The Last Prompt: A 17-Category AI Production Audit
One system prompt that turns any LLM into a senior production-readiness reviewer: 17 categories, PASS/YELLOW/RED, evidence-backed. The gate before you ship
aideveloper-toolsengineeringdevopsopen-source
→
Caveman Prompting: Cut LLM Output Tokens by 65%
A Claude Code skill that makes AI talk caveman cut output tokens 65%, 87% on React debugging. Why brevity makes LLMs cheaper and sharper.
aideveloper-toolsengineeringopen-sourcecontext-engineering
→
HTML in Canvas: The WICG drawElement Proposal
A new WICG proposal renders real, interactive HTML into canvas. The three primitives, privacy-preserving painting, and WebGL support, explained.
aideveloper-toolsengineeringopen-source
→
Microsoft Open-Sourced an Agent Governance Toolkit
Microsoft open-sourced 7 MIT-licensed packages for AI agent governance: identity, policy enforcement, trust scoring, and full OWASP coverage at sub-0.1ms.
aiai-agentssecurityopen-sourceengineeringdeveloper-tools
→
Meta Spent $14.3B on Scale AI, Built Muse Spark in 9 Months
Meta paid $14.3B for 49% of Scale AI, built Muse Spark from scratch in 9 months, and went closed-source. Every benchmark, trade-off, and what it means.
aibusiness-strategyeconomicsopen-sourceengineering
→
AI Is Not Getting Bigger. It Is Getting Smaller.
Jensen Huang made it clear at GTC 2026: the future of AI is not massive proprietary models. It is small, open, and everywhere.
ainvidiaopen-sourceengineering
→
Everything Is a Skill Issue
The models already have the raw capability. The jagged intelligence frontier is not about the AI — it is about you.
aiengineeringdeveloper-toolsproductivity
→
If Your $500K Engineer Isn't Burning $250K in Tokens
Jensen Huang's GTC quote decoded: why AI spending is the new engineering budget baseline.
ainvidiaengineeringbusiness-strategy
→
I Hacked Firecrawl's CTF and Hit #1 on the Leaderboard
10 problems. 45 seconds. Got #1 via an exploit discovery. Here is the full breakdown.
aisecuritydeveloper-toolsengineering
→
We're Getting AI Agent Skills All Wrong
Loading a skills.md into context is just prompt engineering. It does not change the model. Real skills need a different architecture.
aiai-agentsdeveloper-toolsengineering