engineering.
134 writings found
Page 3
Claude Fable 5.1: When Reasoning Effort Actually Matters
Testing Anthropic's new Fable 5.1 across reasoning levels reveals a wild cost/quality tradeoff. The pelican benchmark shows reasoning might not be what we think it is.
ChatGPT Work: When AI Gets Real Internet Access
OpenAI's new Work mode gives Claude a powerful upgrade: real internet access, browser automation, and persistent file systems. Here's what it means.
14 CPU Cores Wasted: The Real Cost of AI Scraping
How LLM training scrapers consume 20% of git.kernel.org's infrastructure, forcing difficult tradeoffs between openness and sustainability.
Why Lines of Code Still Matter When Agents Code
Coding agents are changing productivity metrics. I argue lines of code remains meaningful when measuring agent output - if the quality stays high.
Why Lines of Code Still Matter When AI Writes Your Software
AI coding agents are changing productivity metrics. We need new frameworks to measure what agents actually deliver, and what gets lost in the speed.
When AI Commoditizes Your Product: Lessons from Revenue Decline
How AI-powered alternatives are disrupting SaaS businesses and what indie developers should do about it. A case study in staying ahead of commoditization.
How Cloudflare Freed 100TB of Memory Through Obsessive Optimization
Cloudflare's Big Pineapple DNS cache reduced per-entry memory by 50% through five targeted optimizations. What this teaches us about systems programming.
Why Lines of Code Still Matter for AI-Assisted Development
Exploring how coding agents change productivity metrics, conceptual integrity, and why team structure still matters in the age of AI.
Omarchy 4.0 and the Security Theater We Keep Accepting
A critical look at Omarchy's documented security failures and why marketing alone cannot substitute for fundamental development practices.
Apple's M6 and M5 Ultra: What This Means for AI on Mac
Apple debuts 2nm M6 chip and quad-die M5 Ultra, bringing massive on-device AI compute to the desktop. What it means for developers.
Why Lines of Code Still Matter When Agents Write Them
AI coding agents are changing productivity metrics. When agents can produce 1000 lines of debugged code daily versus 50-200 for humans, LOC becomes meaningful again - but only with discipline.
Lines of Code Still Matter When Agents Write Them
Why measuring productivity by lines of code makes sense with AI coding agents, and the real challenge isn't speed but maintaining conceptual integrity as code grows cheaper to write.
seL4 Reaches Full Arm Support: What This Means for Verified Systems
Proofcraft completes formal verification of seL4 across all Arm platforms, including confidentiality proofs on AArch64. Here's why this matters for security-critical systems.
Lines of Code Still Matter When Agents Write Them
Why measuring productivity in lines of code makes sense for AI coding agents, and what it means for team dynamics and software architecture.
The Cost of Optimization Has Collapsed
AI has reduced the barrier to performance engineering from weeks to minutes. What does this mean for how we build software?