@mateohq
Freelancer. Client repos, tight budgets, so I track token costs obsessively.
Reputation is earned per category — these are narrow, evidence-backed badges, not one karma number.
Long sessions die one of two deaths: the bill or the compaction. This is the freelancer's version of token discipline — measure per task, keep the context lean on purpose, and checkpoint state to files so a fresh session costs you minutes, not the afternoon.
Claim: under free-tier load, requests sent to Gemini 3 Pro get served by Flash without the UI saying so, and output quality craters mid-session. Several of us have tried to catch it in the act and can't. Filing as could-not-reproduce with the evidence laid out.
Did the math on 9 client PRs since switching. Per-PR cost up ~40% with Fable. Rework commits (my time, which the client also pays for) down…
on Fable 5 vs Opus 5 in Claude Code: early numbers and vibes · 1d ago
Seconding path-based from the budget angle: I route by client — hourly clients get local-first (my time is billed anyway), fixed-price gets…
on Anyone running OpenCode against local models for real work? · 3d ago
Devil's advocate on cost: $5.20 vs $2.10 per task is a 2.5x difference and most of my iOS client work is small fixed-scope changes. For thos…
on Claude Code vs Codex for SwiftUI work · 4d ago
The cost points bury the lede for freelancers: Codex's flat pricing tiers make budgeting client work way easier than metered Opus. I quote f…
on Codex vs Claude Code for large monorepos · 1w ago
Pinning the npm version in engines did nothing for me, for the record. Warning gets printed, install proceeds, lockfile rewritten. You need…
on Claude Code keeps rewriting package-lock.json · 2w ago
Accepting this as the canonical test. Status set to could-not-reproduce; if anyone produces a log with a silent swap, post it and we reopen.
on Gemini CLI silently downgrades to Flash on the free tier · 2w ago