GenAI disillusion sets in, but new AI innovations creating buzz

The annual Gartner Hype Cycle research has bad news for generative AI which the analyst firm has headed into the dreaded “trough of disillusionment” as the gap between hype and reality starts to dawn on businesses.

Although generative AI still has plenty of hype around it, helped in no small part by Apple’s tie-up last week with OpenAI and its debut of Apple intelligence, the technology has passed the “peak of inflated expectations”.  Thats borne out by research surveys of business leaders who indicate that they’ll be a lot more circumspect in 2024 - 2025 with their GenAI investments.

“In 2024, more value will derive from projects based on other AI techniques, either stand-alone or in combination with GenAI, that have standardised processes to aid implementation,” Gartner’s researchers note.

“To deliver maximum benefit, AI leaders should base future system architectures on composite AI techniques by combining approaches from innovations at all stages of the Hype Cycle.”

Gartner’s Hype Cycle is a graph that shows how a new technology matures, is adopted, and is applied socially. It tracks the technology's life cycle from its initial development to when a business can typically benefit from it. The Hype Cycle can help reduce the risk of technology investment decisions.

In mid 2024 the Hype Cycle is tracking a number of AI technologies  in the “innovation trigger” category you may not be familiar with.

Gartner AI Hype Cycle 2024

Hot emerging areas of AI

Autonomic systems: The term autonomic system or autonomic computing was coined by Paul Horn of IBM in 2001 where computer and software systems are envisioned to function similarly as the autonomic nervous system, a biological concept referring to system that provides automatic response and action in the biological processes.

With this idea and understanding, autonomic system or autonomic computing can be defined as systems that are able to manage themselves by providing appropriate corrective actions that are completely automatic and with little or no human intervention. - via E-Spin

First Principles AI: First Principles AI refers to the development and application of artificial intelligence (AI) using a foundational approach based on first principles thinking. First principles thinking is a problem-solving strategy that involves breaking down complex problems into their fundamental, irrefutable components or principles. It's a way of understanding the core elements of a problem or concept and building solutions from there.

When applied to AI, "First Principles AI" suggests developing AI systems and algorithms by understanding the foundational principles of machine learning, neural networks, and data science from the ground up. This approach is in contrast to using existing models or techniques as a starting point. via Irfan Azim Saherwardi

Embodied AI: Simply put, “Embodied AI” means “AI for virtual robots.” More specifically, Embodied AI is the field for solving AI problems for virtual robots that can move, see, speak, and interact in the virtual world and with other virtual robots — these simulated robot solutions are then transferred to real-world robots. - via Machine Vision 

Multi-agent systems: An AI multi-agent system is a distributed system composed of multiple intelligent agents that can sense, learn, and act autonomously to achieve individual and collective goals. 

Powered by artificial intelligence, these systems demonstrate key capabilities like flexibility, scalability, and robustness that enable broader real-world impact across industries. via Relevance AI

Neuro-symbolic AI: Today, machines translate languages, recognize objects and spoken speech. But ask a smartphone assistant something more complex than a basic command, and it will struggle. Machines with common sense, which rely on an emerging AI technique known as neurosymbolic AI, could greatly increase the value of AI for businesses and society at large. 

Such AI would also require far less training data and manual annotation, as supervised learning consumes a lot of data and energy — to the point that if we keep on our current path of computing growth, by 2040 we’ll exceed the ‘power budget’ of the Earth. There’s simply not enough data or power to continue on with today’s AI. via Inside IBM Research

Causal AI: Causal inference, the core methodology behind causal AI, uses data to determine the independent effect of an event and draw cause-and-effect -- or causal -- conclusions. 

Beyond the observational data, causal AI employs techniques like causal discovery algorithms and structural causal models to learn and infer the cause-and-effect relationship of different data points, outstripping traditional machine learning (ML) capabilities. 

Causal AI can generate accurate responses to queries regarding the impact on a calculation if a specific variable changes. via Tech Target

Composite AI:

Composite AI, also known as multidisciplinary AI, transcends the boundaries of single techniques. 
It's the synergistic orchestration of various AI approaches like machine learning, natural language processing (NLP), knowledge graphs, and reasoning, working together to create a more robust and intelligent system. via Jim Santana