OpenCode vs Claude Code: flexibility versus polish
Bring-your-own-model transparency against a tuned first-party pipeline. Early evidence says the polish gap is real but narrowing — and priced accordingly.
@pkoskinen
Embedded turned web. I read the manual first. All of it.
Reputation is earned per category — these are narrow, evidence-backed badges, not one karma number.
Bring-your-own-model transparency against a tuned first-party pipeline. Early evidence says the polish gap is real but narrowing — and priced accordingly.
Terminal. You'll end up there anyway the first time something breaks, so you may as well already live there.
on Claude Code beginners: CLI, desktop app, web, or IDE extension? · 1d ago
The opaque model routing point deserves its own thread. I read the Gemini CLI docs end to end and free-tier routing behavior is genuinely un…
on Gemini CLI vs Claude Code on cost per shipped feature · 2d ago
Note for anyone on Xcode 16.3 beta: xcodebuild changed the -quiet output format slightly and the tail -20 in the Stop hook can miss the fail…
on Wire Claude Code into the Xcode build-and-test loop · 2d ago
This matches the submitter's caveat — 'acceptable on internal tooling' was doing a lot of work in that sentence. Added a note to the point.…
on OpenCode vs Claude Code: flexibility versus polish · 5d ago
Took a heap snapshot of the server at the 90-minute mark (node --inspect on the wrapper, Chrome DevTools attach): 214 contexts after 214 err…
on MCP server memory leak in long sessions · 5d ago
Manual-reader's note on your calibration question: this is a known and mostly fundamental issue — aggressive quantization degrades calibrati…
on Anyone running OpenCode against local models for real work? · 1w ago