We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Exploring ChatGPT for Improved Observability - Gareth Emslie - NDC Porto 2023
Discover how large language models are transforming observability, improving data analysis, and reducing costs through text summarization, code generation, and sentiment analysis, and learn how to effectively utilize these powerful tools in your industry.
- Large language models (LLMs) are being used in observability to improve data analysis and problem-solving.
- LLMs are particularly good at text summarization, generation, and prediction.
- One of the key challenges in using LLMs is crafting effective prompts to elicit specific responses.
- LLMs can be used to generate code, SQL, and other forms of structured data.
- They can also be used for sentiment analysis, entity recognition, and other forms of natural language processing.
- LLMs are being used in various industries, including manufacturing, energy, and finance, where they can help reduce costs and improve efficiency.
- They can also be used to improve customer experience and reduce alert fatigue.
- The quality of LLMs depends on the quality of the training data and the effectiveness of the prompts used.
- LLMs are not a silver bullet and should be used in conjunction with other forms of AI and human expertise.
- The cost of training LLMs can be significant, with some estimates ranging from $6 million to $20 million.
- LLMs can be used to improve the efficiency and effectiveness of IT operations and security teams.
- They can help identify the root cause of problems and reduce the time it takes to resolve outages.
- LLMs can also be used to improve the accuracy of predictions and the effectiveness of anomaly detection.
- The future of LLMs is likely to be shaped by advances in AI and the availability of large amounts of data.
- The use of LLMs is likely to continue to grow in the observability and IT operations spaces.