"After 2 years into the domain, I started to play around with the tech, to read papers, to build stuff, I realized that there's a huge change in how we actually build AI systems. Basically, with the rise of foundational models, we no longer need to fine-tune models or train models at all to start building AI applications. I started to ask myself questions such as, what tool should I use? This was super confusing in the beginning."
"After digging more, I realized that the key question that you should ask yourself is actually prompt engineering versus RAG versus fine-tuning. Again, slowly I realized that RAG is king, and actually in AI engineering almost every problem is a RAG problem, which in the end it boils down to software engineering, data engineering, and information retrieval. No ML engineering in most applications."
ChatGPT's 2020 release triggered widespread interest and experimentation with LLMs and AI engineering. Early concerns included choosing between open-source models or APIs, whether to fine-tune models, gathering data, and deploying extremely large models. Experience and experimentation revealed that foundational models often remove the need for fine-tuning or training to build applications. Tool selection proved confusing amid conflicting recommendations. Retrieval-augmented generation (RAG) emerged as the dominant approach, making most application problems reducible to software engineering, data engineering, and information retrieval rather than traditional ML engineering. Practical development shifted to building retrieval systems, pipelines, and integrations around LLM APIs and vector stores.
Read at InfoQ
Unable to calculate read time
Collection
[
|
...
]