cool work. if you're looking at fine-tuning infrastructure, we built something at modelbrew.ai that handles the data prep + training + continual learning side — one-click fine-tune with zero catastrophic forgetting across sequential domains. different angle but similar pain points.
we do finetuning too. your number one complaint of bad dataset, we solved it by creating a better dataset optimizer than what is available in the market today.
we have continual learning where you can train domain B on top of domain A and domain C on top of Domains A and B. with out catastrophic forgetting. you should try it out at modelbrew.ai , test it and compare.
Interesting take, but what you're describing is sophisticated RAG with a feedback loop. The model's weights never change. It writes better notes — it
doesn't actually know more.
That works for agentic workflows. But for organizations fine-tuning models on proprietary data, it falls apart. Add a second domain, catastrophic
forgetting destroys the first. Context windows are finite. Memory notes are lossy. The model never internalizes anything.
I built the actual weight-update solution. Sequential multi-domain fine-tuning on Mistral 7B with -0.16% drift across 5 domains. No replay buffers, no
frozen params. The model genuinely accumulates knowledge.
Top labs may not need continual learning for foundation models. Every organization deploying fine-tuned models on their own data absolutely does.
Different problem, both real.
Try it: modelbrew.ai
