I'm sure the fine-tuned LLM is cool and useful and you put a lot of work in to it.
I hope for your sake that I'm not typical, but I was put majorly off by the experience, and never even saw the LLM in action. Requiring an email, email verification and credit card info and an auth before showing any examples is unfortunate. It presents as a scam. I'm sure it's not a scam, but you're introducing this in a world already full of scams. You're skipping a lot of necessary trust, confidence and excitement building before onboarding. But, I understand your excitement in just having built it and wanting to eagerly show it off.
Better GPU: The biggest improvement was being able to rent better GPUs and massively expand the dataset—this really boosted the model’s capabilities.
Expanded Context Window: I’ve effectively doubled the model’s “memory,” so it now handles shortcuts with 10-14 actions much more reliably. In testing, it’s done a great job keeping all the steps straight, even for complex workflows.
Fewer Hallucinations: One of the biggest complaints was the model inventing random actions or looping endlessly. After a ton of fine-tuning, that’s mostly resolved. If it still happens, please let me know!
Speed Boost: Probably the biggest change. The model is about 7–8x faster than before, thanks to optimized code and better hardware. No more waiting 15 minutes for a shortcut.
I’m happy to chat or troubleshoot if you notice anything weird!
I hope for your sake that I'm not typical, but I was put majorly off by the experience, and never even saw the LLM in action. Requiring an email, email verification and credit card info and an auth before showing any examples is unfortunate. It presents as a scam. I'm sure it's not a scam, but you're introducing this in a world already full of scams. You're skipping a lot of necessary trust, confidence and excitement building before onboarding. But, I understand your excitement in just having built it and wanting to eagerly show it off.