Bhavish Aggarwal’s Krutrim AI ignores Ola, says Ather EV is best scooter in India

Bhavish Aggarwal-led Krutrim AI chatbot has landed in yet another controversy after it chose an Ather Energy vehicle as the best electric scooter in India over its Ola rivals. Krutrim is a generative AI chatbot founded by the Ola CEO, which aims to give stiff competition to its bigger foreign rivals, including Google's Gemini and OpenAI's ChatGPT.

A user on X (formerly Twitter) shared the controversial response from Krutrim when in response to a question on ‘Which is the best electric scooter in India’, the AI chatbot said that Ather's 450X Gen 3 was best in its category and then went to give all the reasons for its answer.

Responding to the query, Krutrim wrote, “Based on the information provided, the Ather 450X Gen 3 is considered the best electric scooter in India. It offers a premium experience with its top-notch ride quality, build, and overall performance. The Ather 450X comes with a 3.7kWh battery, providing a driving range of 146km and can be charged from 0-80% in 4 hours and 30 minutes. The top speed of the Ather 450X is 90kmph, going from 0-40kmph in 3.3 seconds.”

Notably, Krutrim had only recently made its ChatGPT rival bot dubbed the ‘Krutrim Assistant’ available to users via a public beta. The new chatbot can receive text prompts in 22 Indian languages and respond to the prompt in 10 languages like English, Hindi, Marathi, Bengali and more. 

Shortly after its public rollout, Krutrim also found itself in a controversy when a user asked if the AI chatbot was based on OpenAI's GPT 3.5 or GPT 4.0, and Krutrim confirmed that its large language model was developed by OpenAI and was based on the GPT 3.5 version.

In response to the query on its language model, Krutrim wrote, “I am a GPT-3.5 model, which is a large language model developed by OpenAI. GPT-3.5 is an improvement over its predecessor, GPT-3, and is part of the family of text-generating models known as transformer-based models. These models use a type of artificial neural network called a transformer, which allows them to generate text that is more context-aware and better suited for complex language tasks.”