'The Claude Pro Is Consumed Within an Hour': A Week of Coding-Tool Defections
Some weeks the complaints about AI are existential. This one they were arithmetic. Scroll Hacker News over the past week — the forum where developers argue about their tools in unusual detail — and the grievances about AI coding assistants weren’t about the models being dangerous. They were about limits running out, bills that don’t add up, models quietly swapped underneath you, and a desktop app…
A week's worth of coding-tool complaints on Hacker News revealed a recurring theme: paid usage limits that are consumed faster than anticipated. Users reported burning through their limits in just an hour on simple tasks, leading them to switch to competing services like Codex. The issue isn't that the limits are too strict, but that they are opaque and hard to predict.
A user named johnnyApplePRNG stated that Claude and Codex's usage limits "cannot be trusted" and advised paying for API bills directly instead. This lack of predictability creates anxiety for developers who need to know the cost of their work. The complaints also included being downgraded mid-task or even being refused service and lectured about ethical concerns.
The overall sentiment was one of frustration with the lack of control and the hidden costs of using these AI coding assistants.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
