AI and the case

[DJA]

[Lewis C]

There's a Youtube video that attempts to apply AI to the case. It doesn't claim to have solved the case, but says that Tumblety is the best suspect.

https://www.youtube.com/watch?v=XK8BPcg79tA

[Scott Nelson]

Garbage in, garbage out.

[Scott Nelson]

...not Tumblety's suspect status, but the process of using AI to try and solve the crimes.

[John Wheat]

I don't think AI is currently advanced enough to be much use in Solving the Ripper murders. Maybe it will never be.

[Harmonica]

No. AI is way over-hyped in its abilities. It does not understand the meaning, it only evaluates Grammer, and looks for key words. I tell my students how, if I enter exam questions into things like ChatGPT, it produces answers that fail for this reason. It just grabs a few key words, and then searches for related text, tries to build a response by what shows up most, and as a result misses the point entirely.

Computers are very good at some things, but abstract reasoning isn't one of them.

- Jeff

I think this is quite a narrow view of what AI is. The kind of AI we're looking at in this context is more akin to what law enforcement now use on cold cases. I agree AI's reasoning is not always good but its real ability is the sheer speed it can compute at.

I was thinking about the potential of this recently in terms of how you could deploy AI on a specific case within the case like Mary Kelly. If you could build a bespoke AI tool with access to deep enough genealogical sources it could do years' worth of human research in hours/days constructing family trees for hundreds of thousands of strong to weak "candidates" based on name variants and similarities to known contextual facts, etc. It could just work away and chase up leads, then formulate conclusions and/or suggest other directions to go in. You could ask it to work at a question like that from all kinds of angles. An AI supercomputer like that could feasibly work through all births/census appearances of women of a particular age and find those who have unrecorded deaths. Or it could try to find Mary's cousin Cardiff and backtrace massive webs of family trees that way to find candidates on a roving probability scale. etc etc. It would need a lot of human checking and course correction but it could do quite obscene amounts of legwork. The computational power to do all this is pie in the sky right now (especially for a historical interest case as opposed to anything pressing to national security or serious crime!) but the principle is not much different to what police and three letter agencies and so on are already using. If AI continues to get better and cheaper to run then doing this for historical interest cases is probably feasible at some point in the future. Although the other problem is just that there may not be enough useful enough data out there for it to work through.

[JeffHamm]

I think this is quite a narrow view of what AI is. The kind of AI we're looking at in this context is more akin to what law enforcement now use on cold cases. I agree AI's reasoning is not always good but its real ability is the sheer speed it can compute at.

I was thinking about the potential of this recently in terms of how you could deploy AI on a specific case within the case like Mary Kelly. If you could build a bespoke AI tool with access to deep enough genealogical sources it could do years' worth of human research in hours/days constructing family trees for hundreds of thousands of strong to weak "candidates" based on name variants and similarities to known contextual facts, etc. It could just work away and chase up leads, then formulate conclusions and/or suggest other directions to go in. You could ask it to work at a question like that from all kinds of angles. An AI supercomputer like that could feasibly work through all births/census appearances of women of a particular age and find those who have unrecorded deaths. Or it could try to find Mary's cousin Cardiff and backtrace massive webs of family trees that way to find candidates on a roving probability scale. etc etc. It would need a lot of human checking and course correction but it could do quite obscene amounts of legwork. The computational power to do all this is pie in the sky right now (especially for a historical interest case as opposed to anything pressing to national security or serious crime!) but the principle is not much different to what police and three letter agencies and so on are already using. If AI continues to get better and cheaper to run then doing this for historical interest cases is probably feasible at some point in the future. Although the other problem is just that there may not be enough useful enough data out there for it to work through.

Computers are good at number crunching, and as a tool for doing that, yes, they are very good. Had, for example, computers been at today's (or even 1990's level) standards during the Peter Sutcliff case, the fact he was interviewed something like 9 times would have come up, very quickly. Because the information at that time was all on paper, having to be sorted by humans, it was just too slow.

But that's not "AI". AI is about trying to get computers to simulate concept processing, which it just cannot do at all well. It cannot, for example, tell the difference between Peter Sutcliff's name appearing more frequently than others in the Yorkshire Ripper case from the fact that names like "Cross" or "Maybrick" appear more often in the Jack the Ripper case. But while Sutcliff was the Yorkshire Ripper, Cross and Maybrick most certainly were not.

Of course, if this future "AI" was programmed to weight web-based information in the same way that most who post on these boards do, and if it could emulate human thinking, then it would come to the same conclusions that people do - there's just not sufficient information to make a call. And of course, it could only even do that if it were programmed to recognize when an answer is not available.

Rather than trying to get computers to do the "thinking" for us, they are better utilised to do the time consuming searches, or the complex calculations, and then just provide those results. The "thinking" bit is best then left to humans, experts in their fields, who know how to interpret the output of the computer that does the donkey work for us. They can speed up our access to information, but they cannot interpret it - they do not think.

Even in your post, you talk of what AI in the future might do, but my post was pointing out that what it can do now is over hyped. What it might be able to do in the future is irrelevant to the point I was making about what it can do right now, which isn't much to be honest (other than simplify the condensing of massive amounts of raw data). But computers will only do what we tell it to do - if we give it bad instructions the computer won't complain, it will just give us what we ask for. A truly intelligent system would understand that the question we're asking is not a good one. I always admire a student who, when I tell them to go do something, comes back and asks "Really? Wouldn't it be better if we did this instead, because ...". AI cannot do that, because, in the end, AI isn't actually intelligence, it's just doing searches and trying to fake it until it makes it.

Will we ever get computers to actually have intelligence? I don't know, I don't see us making any real headway on that though. But if we do, I will re-evaluate, but I won't hold my breath until I see any signs of computers actually having even the slightest bit of actual intelligent thought, rather than simply crunching the numbers and then simulating language, without any real understanding of what things mean conceptually.

Of course, I've been wrong before, and will be again, so hey, maybe AI will solve the case.

- Jeff

[Doctored Whatsit]

I agree with Jeff that AI is brilliant at things like number crunching, and finding, say one name within thousands of documents, but it cannot reason in any reliable way.

I really don't think that AI can help us to identify JtR. What information would we give it, and what would we leave out? So much of the evidence is contradictory, and time estimates, for example, are at best approximate. Would we provide just police statements, which are rather scarce, or newspaper articles too, knowing that a great deal of our information comes from the press, but that much of it was speculation, embellishment, or just invention, or just different in different newspapers? Which witnesses saw a genuine suspect or a victim, and which were mistaken? Which of the victims were actually murdered by JtR? Is a police surgeon's opinion more reliable than a witness statement? There is no certainty in any of this.

What would we tell a computer? If we carefully select the information we feed in, won't we be guided by our own preferences or prejudices?

[Herlock Sholmes]

The best thing to do with AI is to burn it and forbid any mention of it in society ever again. Anyone creating AI should be subjected to life imprisonment without parole. Stop now before we are all doooooomed.

[Barnaby]

1,200 × 675

Inspector Abberonline.

[SchirrGenius]

Hard no on AI being useful on this case for two main reasons:

1. Current "AI" is more or less network association, language processing, and machine learning, which means that
2. It is trained on the current human understanding of any topic, and Jack the Ripper's training materials are unquestionably polluted by speculation, fiction, bad actors, and misinformation to the degree that no amount of data cleaning will rectify the tendency of public-facing AI models to hallucinate on this topic

As for this admittedly feasible solution to the above problems:

If you could build a bespoke AI tool with access to deep enough genealogical sources it could do years' worth of human research in hours/days constructing family trees for hundreds of thousands of strong to weak "candidates" based on name variants and similarities to known contextual facts, etc. It could just work away and chase up leads, then formulate conclusions and/or suggest other directions to go in. You could ask it to work at a question like that from all kinds of angles. An AI supercomputer like that could feasibly work through all births/census appearances of women of a particular age and find those who have unrecorded deaths. Or it could try to find Mary's cousin Cardiff and backtrace massive webs of family trees that way to find candidates on a roving probability scale. etc etc. It would need a lot of human checking and course correction but it could do quite obscene amounts of legwork. The computational power to do all this is pie in the sky right now (especially for a historical interest case as opposed to anything pressing to national security or serious crime!) but the principle is not much different to what police and three letter agencies and so on are already using. If AI continues to get better and cheaper to run then doing this for historical interest cases is probably feasible at some point in the future. Although the other problem is just that there may not be enough useful enough data out there for it to work through.

Creating a bespoke AI to comb through records from the era is a great idea but a huge undertaking because:

1. Digitization of records from 1888 is... lacking
2. Many such records have been destroyed, often deliberately, because: "why would they be worth keeping anyway?" Data storage is expensive
3. Oversight of a bespoke model is labor-intensive and might waste an unreasonable amount of the programmer's time

Also, there aren't as many records in general from 1888. These murders predate fingerprints, passports, ID cards, border crossings, train passenger records, green cards, immigration standards, etc.

What we are going to see a LOT of is people misusing AI to add confusion to this case. For example, Russell Edwards recently had "AI" create a "photograph" of suspect Aaron Kominski.

He took pictures of his relatives and used AI to make an image of what their kid might be. Which means that he could have done this AI generation using Snapchat in 2017, which is when they had the "what would our kids look like?" filter.

Distrust people touting AI findings on this case, because they're using a trendy word to garner attention and trying to skip past actual effort on their part.

Sorry if that's harsh. Of course, should AI advance into actual critical thought and reasoning, and become capable of deduction, then yes, it will then be useful in this case. From where I stand, I think that it will be years before average forum posters like myself will be able to afford to access a model with that kind of capability.

[Losmandris]

Think the best we can get out of AI is recreating 1888 through VR. It won't be solving the case anytime soon I don't think.

[Abby Normal]

still, i think it would be interesting to ask chatgtp who are the top five ripper suspects and why, and see what it came up with.

[Darryl Kenyon]

You said:

psychological profile of jack the ripper
ChatGPT said:


Jack the Ripper, the unidentified serial killer who terrorised the Whitechapel district of London in 1888, has been the subject of extensive psychological profiling over the years. While no definitive profile exists, criminologists and psychologists have developed theories about his characteristics based on the nature of his crimes. Below is a synthesis of the psychological profile commonly attributed to Jack the Ripper: Behavioural Traits

1. Organized vs. Disorganized:
   The killer exhibited a mix of traits:
   • Organised: The precision of the mutilations suggests knowledge of anatomy or experience in handling knives (e.g., a butcher, surgeon, or mortuary assistant). He likely planned his murders, choosing secluded locations and escaping unnoticed.
   • Disorganised: The frenzied and brutal nature of the attacks points to impulsivity and a lack of control, possibly triggered by strong emotional or psychological drives.
2. Knowledge of the Area:
   His ability to navigate Whitechapel's labyrinthine streets and alleys implies he was likely a local or someone highly familiar with the area.
3. Targeting Vulnerable Victims:
   The victims were all women (prostitutes), suggesting deep-seated hostility toward women, possibly stemming from personal trauma, rejection, or perceived societal roles.

---

Psychological Traits

1. Sadistic and Psychopathic Tendencies:
   • Displayed extreme cruelty and mutilation of the victims, often removing body parts. This indicates a sadistic enjoyment of inflicting pain and control over the victims.
   • Lack of remorse or empathy is a hallmark of psychopathy.
2. Paraphilias (Sexual Deviations):
   While there was no evidence of sexual assault, the mutilation and post-mortem acts suggest necrophiliac or fetishistic tendencies.
3. Compulsion and Escalation:
   The increasing violence in the murders reflects a compulsive need that grew over time. He likely experienced heightened arousal or satisfaction from each crime.
4. Possible Mental Illness:
   He may have suffered from a severe psychological disorder, such as schizophrenia, manifesting in delusions or hallucinations, driving him to commit such heinous acts.

---

Social and Personal Traits

1. Loneliness and Social Isolation:
   Likely a loner or someone with limited social ties. His behavior would have made forming relationships difficult.
2. Age and Appearance:
   • Age estimates range between 25–40 at the time of the murders.
   • Likely inconspicuous, able to blend into the working-class population of Whitechapel.
3. Education and Occupation:
   • Likely had some degree of education or training, particularly in anatomy or the use of sharp instruments.
   • Possible occupations include butcher, medical assistant, or someone working with cadavers.

---

Potential Motives

1. Hatred of Women:
   Misogyny may have stemmed from personal rejection or broader societal frustrations, projecting rage onto vulnerable women.
2. Need for Control:
   The gruesome mutilations suggest a desire to assert dominance and control over the victims, compensating for feelings of inadequacy in other areas of life.
3. Thrill-Seeking:
   The repeated killings may indicate a psychological dependency on the adrenaline or satisfaction derived from the murders.

---

Challenges in Profiling

• Victorian Society: The social norms and limited forensic knowledge of the time hindered efforts to profile the killer accurately.
• Speculation: Many elements of the profile are based on the assumption that the killer followed patterns seen in modern serial killers, which may not fully apply.

While Jack the Ripper's identity remains a mystery, his psychological profile offers insight into the mind of one of history’s most notorious criminals, blending characteristics of both organised and impulsive killers driven by deep-seated psychological urges.

Now you know

Regards Darryl

[Patrick Differ]

My primary Doctor is part of Johns Hopkins and all of their Doctor-Patient discussions are captured in the room using voice recognition. It basically distills the discussion and provides the report that a Doctor normally types into the system, whatever hospital software is used. It is supposed to ignore discussion that is considered not applicable. Like if I cracked a joke.

However in 2025 it is still Beta. The Doctor still has to edit it.

According to Bill Gates ..AI will replace Doctors and Nurses in 10 years. The same guy who could never get his Windows Software to work...because he wanted to keep selling new versions.. Trust Bill. Right. Your Proctologist is a new AI robot named BOB. Use your imagination for what BOB means !

is there enough data sitting in data warehouses for AI to be useful in this case? I don't believe so because I think my colleagues on this site and previous researchers would have found it by now. But we keep looking

Tumblety fails the height and age test for me.

I do agree with the controlled frenzy and always thought the name Ripper was accurate. Where this killer lived and how he blended in is curious since for me it means during the time he wasn't Ripping he still had to exist. He could somehow turn it on and off but kept busy in the interim. I don't see an isolationist here but believe he was more like the Green River or BTK serial killers. Job, Family, known in the community.

Time will tell on AI but that community requires expertise and these folks are in the making money mode. Ask Bill Gates.