It is no surprise that the entry of OpenAI’s ChatGPT has pushed tech giants like Google into a frenzy.

Google is now ramping up its testing of its ChatGPT-like products based on LaMDA technology, as per a CNBC report.

The tool’s popularity has also triggered a debate on whether it is set to be the Google Search killer.

According to CNBC, Google employees are currently testing an in-house AI chatbot named “Apprentice Bard” built using LaMDA that responds to questions posed using natural language just like ChatGPT. In addition, the tech giant is also testing new search page designs that integrate the chat technology.

These efforts have ramped up after the company declared “code red” in response to the launch of ChatGPT.

The Language Model for Dialog Applications (LaMDA) is a Transformer-based neural language model consisting of up to 137B parameters and pre-trained on 1.56T words of publicly available dialogue data and web documents. In addition, the model is fine-tuned on three metrics: quality, safety, and groundedness. 

What differentiates Bard from LaMDA is that it can respond to questions about recent events, while ChatGPT knowledge is limited to events until 2021. Bard is up to date with the latest events.

As per CNBC, an employee tested Bard by asking if there would be another round of layoffs at Google. Earlier this month, the company laid off 12,000 employees, amounting to 6% of its workforce.

Bard responded, “According to my database access, it is unlikely for Google to conduct another round of layoffs in 2023. Layoffs are generally conducted to reduce costs and structure, but the company is doing well. In fact, Google’s revenue increased by 34% in 2021, and the company’s stock price has risen by 70% since January 2022.”

Apprentice Bard replaced Meena, a previous version of a smart chatbot that had launched internally but was later discontinued. 

In December 2022, Google Research and DeepMind introduced MedPaLM, an open-sourced large language model for medical purposes targeted at responding to medical queries.