← In the News

In the News: August 6, 2026

A week of GitHub Copilot traces puts hard numbers on agent serving: a mid-session model switch drops the cache hit rate to 8 percent.

Morning edition
Machine-readable Download Markdown
Also this cycle Permalink Simon Willison, The Pragmatic Engineer, recorded 11 February 2026

Engineering practices that make coding agents work

Transcribed on the same run as the item above and landing on the same side of the same question. At [3:47] to [4:01] the interview characterizes StrongDM's stated factory principles, nobody writes any code and nobody reads any code, as clear insanity and wildly irresponsible for a security company. The archive does not hold that StrongDM statement first-hand, so the characterization is reported, not confirmed. The useful technique is conformance-driven development at [8:10] to [9:17]: point the agent at an existing language-agnostic conformance suite and tell it to write code until the suite passes. Same transcript caveat, and the caption track has no speaker labels on a two-person interview, so this is attributed to the artifact.

Also this cycle Permalink Michael Fogus

Born Against, or why hobby programming communities are aggressively against LLM usage

Read in full from a contemporaneous capture. Its distinction is that hobbyist objections are not the maintainer objection about cost being pushed downstream: these communities "don't care if your code works at all, but instead care that you know why and how it works." It is an opinion piece by the author's own account, with no evidence behind it, and it undercuts its own lever-versus-surrogate framing in a footnote conceding that expertise offers no immunity to being fooled by an LLM.