LLMs and Complex Business Problems

David Ferruchi’s new article “Large Language Models Created Demand for AI Capable of Complex Reasoning They Can’t Deliver Alone” explains why a more holistic approach to AI combined with different forms of reasoning is needed to help us make better decisions. David raises a crucial question: How can we ensure the quality of LLMs when solving complex business problems where the outcome needs to be 100% accurate and provide the long chain of precise reasoning steps? LLMs alone do not, and will not, meet this expectation based strictly on how they work. David dives deeper into the very notion of precision, complex reasoning, and step into the fascinating realm of language itself. Link

Posted in Decision Intelligence, LLM, Reasoning | Leave a comment

DecisionCAMP-2024 Program Announcement

DecisionCAMP is the major annual gathering of practitioners dedicated to Decision Intelligence technologies including Rule Engines, Machine Learning, Optimization, and Generative AIThe Org Committee has just announced a great Program for the 2024 event. Register for free and attend all sessions online.

Posted in DecisionCAMP, Events | Leave a comment

How to Introduce Optimization

Prof. Warren B. Powell published a new book “A Modern Approach to Teaching an Introduction to Optimization“. He states: “Optimization should be the science of making the best decisions we canThe vast majority of optimization problems are used to make decisions that arise over time, which means they are sequential decision problems that have to be solved as new information continues to arrive. While he concentrates on the question “We need to modernize how we introduce students to optimization“, many of his observations are valid for bringing the optimization approach and supporting tools to business analysts. Free PDF

Continue reading
Posted in Decision Making, Optimization | Leave a comment

Text to Knowledge Graph

Dan Selman published an article that describes how to convert natural language text to knowledge graphs. Dan extended Concerto Graph by adding a new method mergeTextToGraph which simplifies the conversion of a block of text to a Knowledge Graph ensuring that the structure of the nodes and edges conforms to the Concerto data model that is associated with the Graph Model. All source codes are available and you may try to test it with your own data models. Link

Posted in Knowledge Representation, LLM | Leave a comment

Progress Towards the Holy Grail

In 1996 Prof. Gene Freuder wrote the paper “In Pursuit of the Holy Grail” proposed that Constraint Programming was well-positioned to pursue the Holy Grail of computer science: the user simply states the problem and the computer solves it. For the last 7 years he runs a series of workshops aims to encourage and disseminate progress towards that goal.

This year workshop will be held on Sep 2. It includes a panel discussion “Have Chatbots Reached the Holy Grail?”. The answer is presumably “no, but”. Why not? What progress do they embody? How can we get closer? Neuro-symbolic, bespoke chatbots, coping with hallucinations, beyond LLMs, … ? If you would like to participate in the panel, submit a PDF containing a one-paragraph position statement – see Link

Posted in Artificial Intelligence, ChatGPT, Constraint Programming, Events, LLM | Leave a comment

Combining Constraint Solvers and LLMs


David Ferrucci: “Ever wondered how AI can tackle complex enterprise problems with precision and reliability? By combining constraint solvers and LLMs, we can turn natural language into actionable knowledge that drives intelligent applications. This approach ensures that our solutions are not only mathematically precise but also interactive and collaborative.

From acquiring business knowledge to using it to drive problem-solving applications, we bridge the gap between language fluency and precise reasoning. Link

Posted in Constraint Programming, LLM, Logic and AI | Leave a comment

Supply Chain => Decision Intelligence 

Niels van Hove: “Decision Intelligence is a natural evolution in Supply Chain planning & execution technology”

Posted in Decision Intelligence, Supply Chain | Leave a comment

Challenge June-2024 “Stable Marriage Problem”

This challenge deals with the famous stable marriage problem

Given n men and n women, where each person has ranked all members of the opposite sex in order of preference, marry the men and women together such that there are no two people of opposite sex who would both rather have each other than their current partners. When there are no such pairs of people, the set of marriages is deemed stable. Link

Posted in Challenges, Decision Modeling | Leave a comment

Paul Haley takes AI models for a spin

On June 3 Paul Haley, a well-known expert in rule engines and natural language processing, posted “A language model is not enough“. Paul asked AI to help him to pass an exam to earn a private pilot certificate. Read Paul’s description of what happened. Here is Paul’s conclusion: “I am interested in using AI to help people learn.  With recent advances, I wondered how much closer we were to off-the-shelf tutoring using language models. In what follows, it’s clear that current language models know enough to be fantastic tutors, but it’s also clear that they are not very good at reasoning, staying on task, or otherwise pursuing purposeful dialog.”  Link

Posted in LLM | Leave a comment

Postgres is eating the database world

“What makes PostgreSQL so capable? Sure, it’s advanced, but so is Oracle; it’s open-source, as is MySQL. PostgreSQL’s edge comes from being both advanced and open-source, allowing it to compete with Oracle/MySQL. But its true uniqueness lies in its extreme extensibility and thriving extension ecosystem.” Link See also “Radical Simplicity

Posted in Database | Leave a comment