melodi
The Price of Prompting: Profiling Energy Use in Large Language Models Inference
Husom, Erik Johannes, Goknil, Arda, Shar, Lwin Khin, Sen, Sagar
In the rapidly evolving realm of artificial intelligence, deploying large language models (LLMs) poses increasingly pressing computational and environmental challenges. This paper introduces MELODI - Monitoring Energy Levels and Optimization for Data-driven Inference - a multifaceted framework crafted to monitor and analyze the energy consumed during LLM inference processes. MELODI enables detailed observations of power consumption dynamics and facilitates the creation of a comprehensive dataset reflective of energy efficiency across varied deployment scenarios. The dataset, generated using MELODI, encompasses a broad spectrum of LLM deployment frameworks, multiple language models, and extensive prompt datasets, enabling a comparative analysis of energy use. Using the dataset, we investigate how prompt attributes, including length and complexity, correlate with energy expenditure. Our findings indicate substantial disparities in energy efficiency, suggesting ample scope for optimization and adoption of sustainable measures in LLM deployment. Our contribution lies not only in the MELODI framework but also in the novel dataset, a resource that can be expanded by other researchers. Thus, MELODI is a foundational tool and dataset for advancing research into energy-conscious LLM deployment, steering the field toward a more sustainable future.
'I felt I was talking to him': are AI personas of the dead a blessing or a curse?
When Christi Angel first talked to a chatbot impersonating her deceased partner, Cameroun, she found the encounter surreal and "very weird". "Yes, I knew it was an AI system but, once I started chatting, my feeling was I was talking to Cameroun. That's how real it felt to me," she says. Angel's conversation with "Cameroun" took a more sinister turn when the persona assumed by the chatbot said he was "in hell". Angel, a practising Christian, found the exchange upsetting and returned a second time seeking a form of closure, which the chatbot provided.
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.15)
- North America > United States > New York (0.05)
- North America > United States > Massachusetts (0.05)
- Asia > South Korea (0.05)
- Leisure & Entertainment (0.99)
- Law (0.72)
- Media > Film (0.32)
He made a chatbot of his dying mother so he never has to let go
Justin Harrison knows what you're thinking: This sounds like an episode of Black Mirror. He is well aware you probably think it's weird, "creepy, and sort of like mad scientists in a laboratory" tinkering with things they shouldn't. He also knows how quickly that attitude can change, how quickly everything can change, when death fixes its gaze on someone you love. The 39-year-old filmmaker, who lives in Los Angeles, has spent the last two years pouring everything -- his time, his money, his data -- into building a posthumous communication service known as YOV, short for You, Only Virtual. Today, he's got something to show for it.
- Media > Film (0.34)
- Leisure & Entertainment (0.34)