Protecting LLM applications with Azure AI Content Safety

Both extremely promising and extremely risky, generative AI has distinct failure modes that we need to defend against to protect our users and our code. We’ve all seen the news, where chatbots are encouraged to be insulting or racist, or large language models (LLMs) are exploited for malicious purposes, and where outputs are at best fanciful and at worst dangerous.

None of this is particularly surprising. It’s possible to craft complex prompts that force undesired outputs, pushing the input window …

applications artificial intelligence azure azure ai chatbots cloud computing code failure generative generative-ai language language models large language large language models llm llm applications llms microsoft azure protect racist safety software development