Hello and welcome to Eye on A.I.
“Embrace A.I. or get left behind” is the message plastered everywhere since ChatGPT opened the floodgates on generative A.I. Now that OpenAI has released its enterprise tier for the tool, the opportunity— and decision—to jump on the train has quickly gotten very real for businesses. As Eye on A.I. discovered in conversations with various companies, the Enterprise version has delivered the needed peace of mind for some to integrate ChatGPT into their businesses—but there are enough outstanding privacy and security questions that many businesses will continue to hold out.
Employees at design platform Canva have found success using ChatGPT Enterprise to learn new areas of the codebase, troubleshoot bugs, write and fix complex spreadsheet formulas, categorize and analyze free-form data, and extract themes from transcripts and user interviews, according to Danny Wu Canva's head of A.I. products.
Canva, which had already integrated OpenAI technology into features like Magic Write, was among a select group of companies invited to beta test ChatGPT Enterprise weeks before its public launch. “We’re definitely impressed by the quality of responses provided with team members reporting that it’s a time saver and provides practical advice with nearly every use,” Wu said.
Hi Marley, a Boston-based cloud insurance company that has been wanting to tap ChatGPT, finally got its chance to use the tech thanks to the improved security features of the enterprise tier, according to chief product officer Jonathan Tushman.
He cited the ability to sandbox data and that fine-tuning of models will be private to their system, which will be “a big unlock for our customer base and for us.”
“Currently, with ChatGPT, we cannot put sensitive data through their pipes. But with ChatGPT Enterprise, they are not using data from customer prompts to train open A.I. models,” he said. “This is the big thing and the thing we’ve been waiting for.”
This is likely exactly what OpenAI is hoping for with the enterprise tier (as well as a way to start bringing in significant revenue from ChatGPT). But a closer look shows the two tiers may not be as different security-wise as they seem, according to The Register. For example, while OpenAI stressed in its announcement for the enterprise tier that the company will not train its model on customer data, OpenAI actually says it does not use data submitted through the API in any of its tiers to train or improve ChatGPT. Even non-API consumers toying around with ChatGPT can opt out of having their interactions used for training. Additionally, OpenAI says some of its staff can access encrypted conversations taking place within the enterprise tier.
In all conversations regarding ChatGPT and its new enterprise offering, security and data governance seem to be top of mind. And for some, the current state of ChatGPT Enterprise’s security and data management is still not sufficient.
Executives at upskilling platform Degreed, for example, said they don’t envision tapping ChatGPT Enterprise anytime soon, in part due to concerns about security and compliance.
“Given the current A.I. regulation and OpenAI being under regulatory investigation, our clients have concerns about licensing OpenAI as a vendor using its outputs directly in the platform,” said Fei Sha, VP of data science and engineering at Degreed.
This is of particular concern for the company’s EU-based customers, as A.I. systems used in education are categorized as “high-risk” in the recent EU A.I. Act, which would make Degreed subject to higher levels of regulation around transparency, data governance, and other guardrails.
Additionally, ChatGPT Enterprise just didn’t pass the company’s cost-benefit analysis. Licensing any new vendor would trigger a resource-intensive vetting process in which all of the company’s clients would have to give permission and sign new agreements. And while Degreed recognizes the potential benefits LLMs could provide for its customers, Fei said the company is “keeping its options open” for other emerging LLMs and that “A.I. technologies should not be implemented for their own sake.”
In order for the company to consider ChatGPT Enterprise, Janice Burns, chief transformation officer at Degreed, said they’d need to see transparent and measurable privacy and security practices, actionable insights to combat misinformation, and for the biases embedded within the LLM to be addressed, in addition to quality recommendations.
“The excitement of innovation is undeniable,” she said. “But tools like ChatGPT for Enterprise also require guardrails and transparency around privacy and user data to make the technology fit for enterprise adoption.”
Online jewelry retailer Angara is another company that, while excited about the possibilities of A.I. tools, will not be using ChatGPT Enterprise.
Cofounder and CEO Ankur Daga said Angara has been using A.I. tools for over a year to help customers find the right product faster and has seen its website conversion rate increase 20% as a result. The company also has a lot more on its A.I. product roadmap, such as upcoming features that will surface recommendations to customers based on text descriptions or uploaded images.
But when the company ran trials of ChatGPT, they were not pleased with the results. While ChatGPT got it right 80% of the time, the other 20% “can cause us to lose our customers’ trust, which is catastrophic in the jewelry business,” Daga said.
And with that, here’s the rest of this week’s A.I. news.
Sage Lazzaro
sage.lazzaro@consultant.fortune.com
sagelazzaro.com
