Comment by dabinat
5 hours ago
There’s evidence that combining models can achieve frontier-level performance (e.g. OpenRouter Fusion). I’m wondering if that’s the more realistic option: combine Opus with a local model to save on token costs.
5 hours ago
There’s evidence that combining models can achieve frontier-level performance (e.g. OpenRouter Fusion). I’m wondering if that’s the more realistic option: combine Opus with a local model to save on token costs.
I start to believe that adding more and more and more and more and more thinking tokens is the hack that works (this is what gave birth to Fable)