Larger or Smaller LLMs?
Multimodal or Specialized Models?
Inference budget or Training budget?
Latency or Capacity?
Performance & Interoperability or Model Size?
Closedsource or Opensource?
Will Shadow AI continue to rise?
Building on Arthur Mensch's insights, we see the growing adaptability of models. The key takeaway is to prioritize tools that enable customers to fine-tune these models for their specific needs. This user-driven customization will unlock significant performance gains.
Hence why I also believe in open-sourcing models.
Through research Mistral AI found, with better hardware and better models a certain level of latency (overall time taken by LLM to generate full response) can be reached, which shifted their perspective on LLMs as a, in my opinion, "single point of contact" entity to one that can operate in sovereignty?
Smaller, more portable LLMs, I believe have the potential to unlock better user-experience. In the words of Arthur (16:55): "Instead of having assistants that are talking to people... (Multimodal LLM) assistants that think on their own at a sufficient speed with a good user experience."
Excited for whats next!
Top comments (0)