Artificial intelligence, including the currently popular generative AI such as OpenAI's ChatGPT, will provide significant advantages for software developers and greatly improve their work efficiency, according to Mark Porter, Chief Technology Officer of document database manufacturer MongoDB.
"I firmly believe that the hype about generative AI potentially causing developers to lose their jobs is wrong," said Porter in an interview with ZDNet.
"Generative AI can not only help us write code, but also assist us in handling test cases, identifying errors in code, and quickly searching for documents," Porter said.
"It will enable developers to write code with the quality, speed, and completeness we have always wanted."
Porter stated that it is not just generative AI, but also other mature models and technologies that have been around for 15 to 20 years that will change the way developers write code.
Porter met with ZDNet at the MongoDB.local developer conference in New York last week. This conference is one of the 29 developer events held by MongoDB in various cities in the United States and abroad.
Prior to serving as Chief Technology Officer at MongoDB three and a half years ago, Porter held various important database-related positions, including operating relational databases on Amazon AWS RDS, operating core technology development for Southeast Asian ride-hailing service Grab as Chief Technology Officer, and serving in multiple roles at Oracle for over ten years, including as one of the initial core developers of the database.
Porter added, "Artificial intelligence is an accelerator for the developer ecosystem, and I believe that more applications will be developed."
"People often have stereotypes about the time and correctness required to write computer software," Porter said. "I think generative AI will change all of this in a significant way, and we will be able to write the applications we want at the speed and quality we expect."
An important part of MongoDB's one-day event was the discussion of new AI features in the MongoDB database.
"MongoDB is actually the foundation for hundreds of companies building AI," Porter said. Indeed, the exhibition area of the Jacob Javits Convention Center in Manhattan featured numerous booths from companies such as Confluent, Hashicorp, IBM, and Amazon AWS, explaining how they use MongoDB with their respective software technologies.
Porter emphasized the importance of the new feature in MongoDB that integrates vector values as a native data type of the database. By supporting vectors, developers can store context vectors (representing approximate answers to queries) generated by large language models in the database and then retrieve them using related searches to produce precise answers with necessary recall parameters.
"When a user asks a question to ChatGPT or other large language models, I will get a vector for that question and then put that vector into my database, and then I will request nearby vectors," which will produce a set of related articles, for example, Porter explained.
"Then, I will use these articles to activate my large language model and tell it, 'You cannot say anything that is not in these articles, please use these articles to answer this question.'"
Porter mentioned that large language models can also perform functions such as summarizing long articles. "I like using large language models to make an article more concise."
In this way, there is a division of labor and cooperation between artificial intelligence and databases.
"You would never want to put a large language model into an online transaction processing system," Porter said. "I think you should use large language models where they should be used and use database technology and vector technology where they should be used."
Although other vendors offer standalone vector databases, Porter told ZDNet that integrating this functionality into the database will alleviate the burden on application developers. He said, "This means you don't need a pipeline operation to replicate data between these two databases, and you don't need to manage two different systems. Everything is in one system, where your core data, metadata, and vectors are stored."
Regardless of how future artificial intelligence develops, Porter stated, "It will not make developers lose their jobs.
"Developers will still listen to their customers, listen to their leaders, and decide what to write."
Source: https://www.zdnet.com/article/how-to-use-chatgpt-to-write-code/
Alphabet Q1 paid subscribers reached 350M, fueled by YouTube & Google One. YouTube ad revenue slightly missed at $9.88B amid Premium growth. Total Q1 revenue hit $109.9B, beating forecasts.
Anthropic releases Claude connectors for Adobe, Blender, and Ableton, enabling AI workflow automation and app control. It also sponsors the Blender Development Foundation.
Apple introduces an App Store model splitting 12-month plans into monthly installments. On iOS 26.4+, it lowers upfront costs without reducing total price, adding billing tracking.
Google launches Aadhaar digital IDs in Wallet for India, enabling secure QR/NFC verification. A phased partner rollout targets key sectors, while passport-based credentials expand globally.
YouTube tests "Ask YouTube," an AI tool blending text and video for complex queries. Initially for US Premium users, it supports interactive follow-ups, expanding Google's AI search.
Google grants US DoD classified AI access, joining OpenAI and xAI in defense deals amid Anthropic's dispute. Contractual safeguards against surveillance and lethal weapons remain unenforceable.
Mistral AI launches Workflows, a Temporal-powered orchestration platform for secure, Python-driven enterprise AI automation featuring human-in-the-loop approvals.