Comment by turblety

Absolutely. Thing is, I'd actually rather take a worse model than Anthropic, so long as it's consistent. Like, a model that can successfully do well for 80% of tasks is much better than Anthropic that some days will be 90% other 60%.

When you have a consistent model, you can incorporate fixes/prompts into your workflow to make it behave better. But this, always having to guess if Anthropic has quantised the model today, wastes so much time and effort.