AI is transforming education, empowering students to learn in innovative ways. A recent VentureBeat article highlights Anthropic’s groundbreaking contributions, such as their “Claude Learning Mode,” which encourages critical thinking by prompting students to actively engage with the material. Meanwhile, Northeastern University is embracing AI across 13 global campuses, weaving it into their academic fabric to prepare learners for the future. You can read more about Anthropic's work [1].

Experiment: Microbes and Energy – A Glimpse into AI’s Domain-Specific Expertise

To explore the breadth of AI’s capabilities, I ran a simple experiment comparing insights from Copilot and domain-specific Enspired-GPT on the latest advancements in microbial energy.

Prompt: “What is the latest on microbes use in energy?”

Here’s Copilot's response:

1) Recycling Lithium from Batteries: University of Surrey researchers have developed a microbial-based method that recovers up to 95% of lithium from used batteries. This eco-friendly approach avoids toxic chemicals and high energy consumption, potentially revolutionizing the battery recycling process.

2) Hydrogen Production: Marine bacteria, such as those from the Vibrionaceae family, are capable of producing hydrogen gas by breaking down formate, presenting opportunities for clean hydrogen energy solutions.

3) Microbial Fuel Cells (MFCs): These innovative devices leverage bacteria to convert organic material into electricity. Recent efforts focus on scaling MFCs for deep-sea sensor power, reducing reliance on conventional batteries.

4) Carbon Fixation: A newly discovered microbe transforms carbon dioxide into energy-rich chemicals through a unique metabolic pathway, paving the way for advances in biofuel production.

Then repeat on domain-specific Enspired-GPT [2], here is the response:

A Denver-based company is utilizing microbes. Recovery rates of metals from ores are sometimes as low as 1 percent. University of Waterloo researchers in Canada are altering DNA in bacteria so that the bacteria can break down plastics. These bacteria already exist in water systems to clean up microplastics. Dr. Marc Aucoin, a professor in the Department of Chemical Engineering, describes these bacteria as bio-robots that can be programmed to get the job done. The bacteria target polyethylene terephthalate (PET), a common plastic found in carpet, clothing, and food and beverages containers that can take hundreds of years to degrade. PETs typically break down into microplastics, which are pieces of plastic less than 5 millimeters long. These microplastics enter the food chain and contain chemicals that are associated with insulin resistance, cancer, and decreased reproductive health. Current studies are investigating safety concerns and how well the plastic-eating trait in this bacterium will be passed along when the bacteria multiply. Aaron Yip, a PhD candidate in the Department of Chemical Engineering, said that microplastic degradation in wastewater treatment plants is a safer application to target. Many of these facilities are already designed to neutralize bacteria in wastewater, which would kill any engineered bacteria prior to discharging water back into the environment. Geoscientists are trained to understand and research nutrient and chemical transport in water through a natural system. They can measure the bacteria’s effectiveness, and might be the first ones to know if the bacteria were to ever get out.

Assessment - AI indeed has the potential to usher in a more calibrated structured learning.

Stay curious! Exploring the endless possibilities of learning with AI is just the beginning. Start your journey with the DeepLearning TIG Blog and let us know about your own experiments and discoveries. Together, we can enspire and innovate!

Reference links:

[1] https://venturebeat.com/a...nts-do-the-thinking/

[2] https://enspired-gpt.com/ (refer to TIG Feb 4th 2025 post https://broken.aapg.donfick.com/care...aft/674/groupid/979)