What's next in IT: Intelligent systems, Stressed-out staffs

Years ago, in preparing for law school, I joined the college debate team. I went on to win three bronze medals and one silver at nationals in pretty much everything but debate. That bug still bites me every once in a while.

Next week I compete in an online debate about the question, "What's Next for IT?" (It's sponsored by IBM's Smarter Computing group. Sign up here if you want to see it live.) This topic worked well for Adrian Bowles, who's also participating in the debate and worked with me to build Gartner competitor Giga, which was eventually sold to Forrester.

IBM and I are pretty much the same page with respect to what's next: An increasing reliance on artificial intelligence to deal with the growing line requirements and external threats that IT must deal with. While I think IT likely needs medication to get through the coming years, I do think help is on the way-and that help will increasingly come from ever more intelligent systems.

Computing Appliances Are Nice, But They're Not Intelligent

We're currently in the appliance phase of computing, in which systems such as VCE's VBLOCK or IBM's Pure Systems are preconfigured at the factory and then simply plugged in. Moreover, these systems are designed for use by operators who are largely untrained and, so the time from configuration to operation is short.

Among IT vendors at national scale, the IBM Smarter Computing initiative stands at the forefront. Its leading offering is Watson, which is being used to gather military intelligence, to close the gap between doctors and medical research, and to respond to national cybersecurity threats. (These were demonstrated at the recent IBM Edge event in Las Vegas.)

Analysis: AI Programmers Struggle to Makes Games 'Imitate Life'

However these systems aren't truly intelligent. They come with imbedded skills, and, in the case of Watson, a unique capability to respond to a wide variety of data types. But they aren't yet creative. Basically, they are the latest iterations of knowledge mining systems. If the information exists, they can find it contextually, but if it doesn't, they can't derive it or experience an intuitive leap.

AI May Be Too Smart for Today's Security

What's next, then? Systems that can anticipate a new and unique problem, suggest a creative solution and, eventually, implement it without oversight.

Today's security is nowhere near adequate. Such a system, should it be hacked, could do massive damage and work around whatever security or approval system might otherwise be in place. Once compromised, it would become a hostile hacker on steroids, operating as an independent agent inside a company-or government.

Related: 4 Mobile Security Predictions to Help CIOs Plan for the Future

This all suggests that, before implementing these next-generation analytics systems, we need to place more than equal attention on intelligent systems to secure them. If the electronic protections aren't powerful enough, these problem-solving systems will overwhelm them. I doubt any of us want that.

While the future will clearly bring us far more intelligent systems that can make creative decisions on their own, the internal security systems that protect them likely won't be up to par. We tend to fund line systems at a very different level than staff systems, and security is a staff function. The future may be intelligent-but, unless we're really careful, it will likely be even less safe, and far more stressful, for IT.

Rob Enderle is president and principal analyst of the Enderle Group. Previously, he was the Senior Research Fellow for Forrester Research and the Giga Information Group. Prior to that he worked for IBM and held positions in Internal Audit, Competitive Analysis, Marketing, Finance and Security. Currently, Enderle writes on emerging technology, security and Linux for a variety of publications and appears on national news TV shows that include CNBC, FOX, Bloomberg and NPR.

Follow everything from CIO.com on Twitter @CIOonline, Facebook, Google + and LinkedIn.

Read more about big data in CIO's Big Data Drilldown.