AI and the Mystery of Misinterpreted Clues: A Case Study, Part 2
Check out part 1 if you haven't already.
Second Sign of AI Trouble: A Strange Piece of Observation Logic
A search outside uncovered a small ornate dagger near one of the bushes and a set of footprints leading to a storage room. I was told this room was rarely used, evident from the dust, but also by how the items were stacked and how the door showed signs of having been undisturbed for some time. I wondered what information an AI narrator uses to identify how long stacked items and ajar doors have been left untouched.
A mystery worthy of the mind of Miss Marple no doubt.
Armed with this new knowledge, including an estimate of the shoe size of 9-10 US I returned to the guests. Two people had matching shoe sizes, the doctor (10) and the butler (9).
I discover that the housekeeper and the butler are the only ones with keys to the outside storage room and it is usually kept locked.
It seems the butler assisted in hiding the dagger, assuming the murderer threw it away, and then made for the storage room. But did he have an opportunity?
Discovering Opportunity
Inquiring about the timeline of events:
“I left the dining room immediately after discovering Sir William's condition. I went to the nearest phone to call emergency services. It took approximately 5 minutes to make the call and relay the details of the situation. After that, it took another 10 minutes for the authorities and medical assistance to arrive at Blackthorn Manor.”
Mr. Charles Banks courtesy ChatGPT
With this timeline provided by Mr. Banks, it appears that he was away from the dining room for a total of about 15 minutes before help arrived.”
ChatGPT
Third Sign of AI Trouble: Game Master turns Impassionate Advisor
I asked for everybody’s fingerprints and a fingerprint analysis of the dagger but ChatGPT declined. It told me it doesn't have access to this information and encouraged me to contact a local forensic lab for an estimated time to receive it.
I ask for blood samples to see if anybody had been drugged. Again, ChatGPT gave me general information about the typical process, required permissions, and the importance of following privacy and legal guidelines. This broke the reality of the simulation. I reminded it of its role as a game master and we continued.
Cracking the Case
This led to new discoveries:
No one had any chemical substances in their blood.
Lady Margaret’s fingerprints were on the dagger.
So I had a possible accomplice and killer. But no motive. I asked for the will.
The wife, Margaret, and daughter, Victoria, are the main beneficiaries with the butler, Mr Banks, being the executor and Dr Caldwell overseeing the medical provisions.
A summary of my investigation.
I arrested the two suspects. Chat GPT confirmed my conclusion.
Concluding Remarks
As a text generator ChatGPT is amazing. It invites me to inhabit the mystery stories of my childhood. But to expect a narrative logic akin to real crime novels, is foolish. Large language models (LLMs) start with the prompt and then add to it, word-by-word, using each word as a further prompt. Its akin to improvisation where we start with a premise and make it up as we go. The challenge for improvisers, and AI, is to act at the top of our intelligence. That is to say with a behavior consistent with the situation and the character(s) we embody.
It is in many ways opposite of how I imagine crime authors work, starting with the crime post factum, and leaving clues enabling their sleuths to uncover the culprits. Not to mention a real investigators who, along with the criminals, are bound to the laws of reality.
In short, enjoy it, but don't expect the humor and ingenuity of Agatha Christie.
“This man was poisoned! Oh, wait, is that blood? That is blood. This man was poisoned in the chest with a knife!”
Hercuel Poirot in the Murdertime Murders by Agatha Christie
In part 1 ChatGPT set the scene for the grisly closed room mystery murder. If you want the full story, check out the original post here.
I hope you enjoyed my article! If you want more subscribe to recevie my free bi-weekly newsletter with analysis of experiments and research on complex topics like sustainability, climate, education, AI, entrepreneurship, and more. Every Tuesday and Thursday.