If one were to use an approach like Six Thinking Hats, one could use a hat sequence such as 1.Blue -> 2.White -> 3.Green -> 4.Yellow -> 5.Black -> 6.Green -> 7.Red -> 8.Blue. Each colored hat represents a specific thinking mode. We assign a predetermined time for each stage and use the thinking mode exclusively related to the hat color.
1.Blue: Establish a focus (for eg: building an app that does X)
2.White: What information do we have (for eg: addressable market size, MVP scope, any research/data available on prospective customers etc.,)
3.Green: The creative details (for eg: We will do Y1, Y2, Y3, ...)
4.Yellow: List the benefits
5.Black: List the drawbacks, pitfalls, challenges, risks etc.,
6.Green: Address the drawbacks, pitfalls and challenges creatively and try to mitigate risks
7.Red: Get a gut check from the team if the proposed idea/solution is trending in the right direction
8.Blue: Setup a follow-up action plan (for eg: Next steps on xx/xx/xxxx, task owner ABC).
The article's main point on putting forward the case against is only the #5.Black hat thinking. We are all natural black hat thinkers. But that is just one of the modes and focusing on that alone doesn't lead to a robust solution.
More on Six Thinking Hats in this book here: https://www.amazon.com/Six-Thinking-Hats-Edward-Bono/dp/0316...
There are numerous examples cited in the book and around the web on how this streamlines discussions (and also gives everyone a chance to chip in from different angles).
Edward de Bono, the person who coined the term lateral thinking, lists random juxtaposition as one of the tools for spurring creativity. [1], [2]
In his Six Thinking Hats [2], he writes about 6 different modes of thinking coded by colored hats.
- Blue hat: Organizing
- White hat: Information, facts, stats
- Green hat: Creative ideas
- Yellow hat: Benefits and positives
- Black hat: Caution, risks, negatives
- Red hat: Emotions
He asks us (a team) to look at a problem (he calls it Focus. For e.g., Focus: AGI in military use) wearing one hat at a time. So, when we all wear White hat, we bring data, citations, previous relevant work etc., We don't expend energy in evaluating this data at the moment (that comes later when we wear a different hat, i.e., the black hat).
His theory is that we can think better with the Six Thinking Hats method.
So, applying this analogy to LLMs, hallucinations of LLMs can be thought of as the LLM wearing a green hat.
A theorem prover or fact checker can be added to act as a black hat. (LLMs themselves are capable of doing this critical review -- for eg., list 5 points for and against fossil fuels).
Extending this analogy further, we have tools like LangChain [3] that are focused on the organizing bit (blue hat), ChatGPT plugins that provide up-to-date information, run computations or use 3rd party services (white hat).
Green and Yellow hats are out-of-the-box supported by LLMs already.
Red hat is a sentimental analyzer (which is a classic machine learning algorithm) that LLMs already subsume.
So, it is just a matter of time before this gets refined and more useful that we don't have to worry about the hallucination coming in the way.
[1]: https://www.amazon.com/Serious-Creativity-Thoughts-Reinventi...
[2]: https://www.amazon.com/Six-Thinking-Hats-Edward-Bono/dp/0316...
[3]: https://github.com/hwchase17/langchain