Developer Tools
Writing filed under Developer Tools.
SWE-bench stopped being enough
When a benchmark stops separating frontier coding systems, teams need local evals more, not less.
Tooling should make the safe path short
Local dev needs an exit ramp
A development loop should tell you how to stop, reset, and recover without reading every script.
GPT-4.1 made coding models feel specialized
Git history should explain the decision
A commit message is one of the cheapest places to preserve why a change happened.
Scripts should be idempotent by default
The best project scripts can run twice without making the second run weird.
Good CLI output is a kind of API
Terminal output should be written for the person debugging at 11 p.m., not for the happy path demo.
TypeScript 5.5 cut some friction from filter code
Inferred type predicates were not flashy, but they removed a small daily tax from TypeScript code.