alt Hacker News> The mentioned other models that are trained for the same purpose with close to the same capabilities.
well they dont tell you that do they? there is no way to tell what model can and cannot do unless you extensivevly test it yourself and pray for the best.
If you don’t have a proper testing mechanism for your product, regardless of the model, you shouldn’t be shipping it. Praying for the best is not a strategy and don’t blame your lack of testing strategy on the LLM capability mismatch