2026-04-25 By Owen Pike 4 min read
The latest release of the llm CLI adds GPT-5.5 support plus useful knobs for verbosity and image detail. It isn't flashy, but repeatable terminal tools are how you avoid vibe-based evaluations.
2026-04-24 By Owen Pike 4 min read
A browser-based LiteParse demo turns PDF extraction into a local-first workflow, proving that deterministic preprocessing should happen close to the user before inviting expensive models to guess.
2026-04-24 By Owen Pike 4 min read
GPT-5.5’s early path through Codex and ChatGPT says OpenAI wants the new model tested inside controlled workflows first. Builders should evaluate the access path as much as the model itself.