Having an expensive 3.5 Opus would be cool, but it’s not my top wish. I’d prefer to have a variety of “flavors” of Sonnet. Different specializations for different use cases.
For example:
Science fiction writer / General Creative writer
Poet
Actor
Philosopher / Humanities professor
Chem/Bio professor
Math/Physics professor
Literary Editor
Coder
Lawyer/Political Science professor
Clerical worker for mundane repetitive tasks (probably should be a Haiku, actually)
The main things missing from Sonnet 3.5 that Opus 3 has are creativity, open mindedness, ability to analyze multi-sided complex philosophical questions better, ability to roleplay convincingly.
Why try to cram all abilities into one single model? Distilling down to smaller models seems like a perfect place to allow for specialization.
[Edit: less than a month later, my wish came true. Anthropic has added “communication styles” to Claude and I really like it. The built-in ones (concise, formal) work great. The roll-your-own-from-examples is rough around the edges still.]
I suspect fine-tuning specialized models is just squeezing a bit more performance in a particular direction, and not nearly as useful as developing the next-gen model. Complex reasoning takes more steps and tighter coherence among them (the o1 models are a step in this direction). You can try to devote a toddler to studying philosophy, but it won’t really work until their brain matures more.
If system prompts aren’t enough but fine-tuning is, this should be doable with different adapters that can be loaded at inference time; not needing to distill into separate models.
Yes, I agree that’s an alternative. Then you’d need the primary model to be less RLHF’d and focused. A more raw model should be capable, with an adapter, of expressing a wider variety of behaviors.
I still think that distilling down from specialized large teacher models world likely give the best result, but that’s just a hunch.
Having an expensive 3.5 Opus would be cool, but it’s not my top wish. I’d prefer to have a variety of “flavors” of Sonnet. Different specializations for different use cases.
For example:
Science fiction writer / General Creative writer
Poet
Actor
Philosopher / Humanities professor
Chem/Bio professor
Math/Physics professor
Literary Editor
Coder
Lawyer/Political Science professor
Clerical worker for mundane repetitive tasks (probably should be a Haiku, actually)
The main things missing from Sonnet 3.5 that Opus 3 has are creativity, open mindedness, ability to analyze multi-sided complex philosophical questions better, ability to roleplay convincingly.
Why try to cram all abilities into one single model? Distilling down to smaller models seems like a perfect place to allow for specialization.
[Edit: less than a month later, my wish came true. Anthropic has added “communication styles” to Claude and I really like it. The built-in ones (concise, formal) work great. The roll-your-own-from-examples is rough around the edges still.]
I suspect fine-tuning specialized models is just squeezing a bit more performance in a particular direction, and not nearly as useful as developing the next-gen model. Complex reasoning takes more steps and tighter coherence among them (the o1 models are a step in this direction). You can try to devote a toddler to studying philosophy, but it won’t really work until their brain matures more.
For raw IQ, sure. I just mean “conversational flavor”.
If system prompts aren’t enough but fine-tuning is, this should be doable with different adapters that can be loaded at inference time; not needing to distill into separate models.
Yes, I agree that’s an alternative. Then you’d need the primary model to be less RLHF’d and focused. A more raw model should be capable, with an adapter, of expressing a wider variety of behaviors.
I still think that distilling down from specialized large teacher models world likely give the best result, but that’s just a hunch.