Las Vegas — At this annual re:Invent conference, AWS today launched new versions of its Nova models that are comparable with the latest model releases from frontier labs like Anthropic, OpenAI and Google. But for many use cases, off-the-shelf large language models (LLM) don’t solve their specific use cases and may not be able to deliver the reliability needed to put a given AI workload into production. Fine-tuning existing open-weight models is often the only option here, but that takes a lot of expertise and can come with its own…
