This adoption has been led by LLMs that promised to fulfill numerous use cases across the digital workplace. However, the failure of LLMs to live up to their hype will be the story of 2024, as generic models become relegated to consumer-centric applications and enterprise users turn to smaller, more targeted AI models, purpose-built to meet their business needs.
LLMs struggle to meet long-term expectations
Over the past year, companies have shown their willingness to experiment with AI. Still, long-term success relies on the ability of AI to solve specific business problems and achieve positive outcomes — and LLMs are failing to meet those expectations. There are growing concerns around the quality, accuracy, and security of these models, to the extent that companies are already prohibiting employees from using ChatGPT to shield their data, and the broader market is filing lawsuits to prevent the use of their data for model training.
This calls into question the long-term sustainability and financial viability of LLMs, which take billions of tokens to train. Without a steady influx of good, clean and cheap data, it will become increasingly difficult and expensive to build, deploy, and refresh models.
