What a great year 2023 has been!
When ChatGPT was published at the end of 2022, I knew it would change the world. I wanted to learn and understand this technology. Fortunately, through my network of friends, managers and mentors I was able to work on Generative AI with some of our biggest clients and partners this year.
I’ve been in the IT industry for several years and have seen a lot. But I’ve never experienced such a fast pace of innovation. Capabilities that are possible and cheap today like fine-tuning of models didn’t seem to be applicable for most companies at the beginning of this year. It also turned out that fine-tuned smaller and cheaper models can be as efficient as really large generic models.
Highlights
As always it has been a pleasure to work with so many smart colleagues at IBM. While I had worked as developer and developer advocate earlier, this year I focused on AI and learned a lot from IBM’s AI experts.
Topics:
- AI and Generative AI
- LLM - Large Language Model
- RAG - Retrieval Augmented Generation
- Prompt Engineering
- Fine-Tuning and GPUs
- AI experiments
- Models: Granite, FLAN T5, LLaMA, Falcon, …
- Semantic searches and vector searches
Key technologies:
- Hugging Face
- Python
- PyTorch
- Open Source
Products:
- IBM Watsonx.ai
- IBM Watson Assistant
- Elastic Elasticsearch
Blog Posts
Check out my blog posts for more.