Hacker News new | ask | show | jobs
by icelancer 236 days ago
I've found this mostly to be the case when using lightweight open source models or mini models.

Rarely is this an issue with SOTA models like Sonnet-4.5, Opus-4.1, GPT-5-Thinking or better, etc. But that's expensive, so all the companies use cut-rate models or non-existent TTC to save on cost and to go faster.