Just in case you haven’t heard, the hot new buzzword (okay, buzz-phrase) is “generative AI.” It’s defined as “… algorithms (such as ChatGPT) that can be used to create new content, including audio, code, images, text, simulations, and videos.”
By now we’ve all been inundated with alarming accounts of generative AI’s societal consequences (including this, from me). And there’s a lot to be alarmed about, from the erosion of reality I wrote about in the referenced KJR to the potential obsolescence of Homo sapiens. To which, let me add this thought, in the interest of being first to ring the bell: What’s the big deal? Thirty or more years ago, pedagogues worried that the advent of cheap 10-key calculators would be the end of mathematics education as we know it. Now, there no longer seems to be much of a point to memorizing the multiplication tables.
The question: In the future, will we look back and wonder what all the fuss was about? Because really, isn’t generative AI’s impact just like that of the 10-key calculator but for verbal skills instead of arithmetic?
As a writer, consultant, and IT industry wiseguy I take such things personally. So to discover whether I’m already obsolete or not, I decided to put generative AI – OpenAI version – through its KJR paces by askingsome questions thatare central to KJR’s mission, starting with this: What are the most important factors in making IT organizations effective?
ChatGPT responded with a 600-word essay. Its core points:
- Leadership and Management
- Skilled Workforce
- Clear Goals and Objectives
- Effective Communication and Collaboration
- Agile and Adaptable Mindset
- Robust IT Governance
- Customer Focus
- Efficient Resource Management
It followed each of these headlines with a concise, explanatory paragraph.
For contrast, here’s the framework I’ve relied on for just about forever – Effective IT masters:
- Business integration
- Process maturity
- Technical architecture
- Human performance
My first reaction to ChatGPT’s answer was dismay. ChatGPT’s essay was, I had to concede, quite good.
But then I compared the two more closely. I’m delighted to report that every element of the ChatGPT framework fits into the KJR framework. Leadership and Management, and a skilled workforce, for example, are two sub-factors among a half-dozen that are subsumed by Human Performance.
The reverse isn’t true – the ChatGPT framework ignores, for example, the impact of a strong technical architecture, not to mention the critical role process maturity plays in the effectiveness of not only IT, but all organizations.
Ready for another? I asked, “What are the eight tasks of leadership?”
The answer (again, just the headlines):
- Setting Vision and Direction.
- Communicating and Influencing.
- Building and Managing Teams
- Making Decisions
- Planning and Organizing
- Managing Change
- Developing Others
- Ensuring Accountability and Results
KJR’s eight tasks:
- Setting direction
- Managing team dynamics
- Engineering culture
Again, ChatGPT’s response was impressive – well-written, concise, and plausible. But digging in, it misses quite a bit. For example, the closest it gets to delegating is “developing others,” but that inverts purpose and fringe benefit.
As for communicating – arguably the single most important of the eight leadership tasks, ChatGPT entirely ignored listening and facilitating.
So I decided to give ChatGPT one more chance: “Is ‘internal customer’ a good idea?”
Its answer was, I have to admit, quite good – how the winning applicant for an open CIO slot might have responded. Again, summarizing:
Positive aspects of internal customer concept:
- Encourages collaboration
- Enhances service mindset
- Emphasizes employee satisfaction
Limitations of internal customer concept:
- May promote silos
- Can blur roles and responsibilities
- May not reflect organizational dynamics
Not bad. Personally, I think it’s too kind, but then I’m heavily invested in the end of the internal customer concept, so I can’t claim to be unbiased.
Bob’s last word: So I asked ChatGPT one more question: Should CIOs consider Bob Lewis a trusted advisor?
Its answer: “As an AI language model, I cannot make specific recommendations about individuals or their trustworthiness. Whether a Chief Information Officer (CIO) should consider Bob Lewis, or any other individual, as a trusted advisor would depend on various factors, including the CIO’s specific needs, goals, and context, as well as Bob Lewis’s qualifications, experience, and reputation.”
“Bob Lewis is a well-known author and consultant in the field of IT management and organizational effectiveness. He has written books on IT leadership and management, and has provided consulting services to organizations on IT strategy, governance, and operations. His insights and perspectives may be valuable for some CIOs seeking guidance in these areas.”
I’ll give ChatGPT points for diplomacy, and I guess I should be pleased that I appear on its radar screen at all.
Bob’s sales pitch: Please don’t think I’m encouraging you to shift your loyalties from KJR to ChatGPT. The latter’s responses are certainly plausible, but that isn’t the same thing as standing up to scrutiny (I nearly said “close scrutiny,” but if it’s scrutiny it’s close by definition).