ChatGPT Comes for 3D Printing with Authentise’s 3DGPT

Conversational AI synthesizes over 12,000 additive manufacturing journal articles and standards.

If you work in 3D printing, you might need to get used to reading these words:

As a language model, my responses are generated based on a mixture of licensed data, data created by human trainers and publicly available data. I should note that while I strive to provide accurate and up-to-date information, my responses may not always reflect the most current news or developments.

For anyone who’s been messing around with ChatGPT and other large language models (LLMs) in recent months—and over 100 million people have, according to the latest statistics from OpenAI—this should be all too familiar.

The explosive popularity of LLMs has led to a concordant growth in domain-specific models for everything from molecular chemistry to finance to coding and now, 3D printing. That’s the premise behind Authentise’s 3DGPT, a large language model designed to act as an AI resource for engineers working with additive materials and processes.

According to an Authentise press release, the 3DGPT LLM can answer both general questions, such as “What additive technologies can I use to 3D print concrete?” as well as more specific enquiries, such as “How do I reduce the likelihood of defects when working with stainless steel in powder bed fusion?”

The answers to both questions are based on training data derived from more than 12,000 journal articles and additive manufacturing standards that were used to construct 3DGPT.

“There are many ways we think that this tool might be useful inside our product portfolio,” said Authentise CEO Andre Wegner in the company’s press release, “whether it’s to help create reliable and efficient workflows or make RFQ’s with many standards references more penetrable. Before that – we, Authentise as well as partners such as ASTM, naturally need to understand the technology’s opportunities and limits; we know that GPT algorithms sometimes hallucinate, for instance.”

While the risk of so-called “hallucinations” (the PR-friendly term for falsehoods unabashedly presented as truths by LLMs) is inherent in any large language model, Authentise is aiming to ameliorate it by having 3DGPT provide references to what the company refers to as “more technical answers.” Based on the limited information in the company’s press release, it’s unclear whether 3DGPT could fall prey to the same issues with citations that recently landed an LLM-using litigator in hot water with a federal judge.

Fortunately, 3DGPT is following in the footsteps of other LLMs in being open for public trials.

Engineering.com has signed up and will be reporting our assessments of 3DGPT’s capabilities in an upcoming article.

Stay tuned.

Written by

Ian Wright

Ian is a senior editor at engineering.com, covering additive manufacturing and 3D printing, artificial intelligence, and advanced manufacturing. Ian holds bachelors and masters degrees in philosophy from McMaster University and spent six years pursuing a doctoral degree at York University before withdrawing in good standing.