The Pros and Cons of Using AI to Prevent Crime

In sci-fi dystopian films like The Matrix, Bladerunner, and The Terminator, pollution clouds the sun, climate chaos worsens, and Artificial Intelligence is the enemy

___________

by Claude.ai

"Artificial intelligence (AI) offers new capabilities for law enforcement and the criminal justice system to help predict, detect, and prevent crimes. As discussed in previous SafeGrowth blogs like "Can AI Make Neighborhoods Safer?" and "Bias and AI - What it Means for Crime Prevention", AI tools such as predictive policing algorithms, facial recognition, and risk assessment systems are increasingly being adopted. However, the use of AI also raises important ethical questions. In this blog, I’ll explore some key pros and cons of using AI for crime prevention.

PROS

• Crime prediction: As noted in "Predictive Policing: The Argument for Public Transparency", AI can analyze crime data to identify high-risk areas in order to optimize police patrols and resources. This data-driven approach can increase efficiency.
• Facial recognition: AI facial analysis can rapidly compare faces to databases of photos to identify suspects or missing persons. This expands investigation capabilities, as examined in “Facial Recognition Software and Crime Prevention”. 
• Risk assessment: As discussed in "How AI is Transforming the Criminal Justice System", AI algorithms can assess recidivism risk to inform bail and sentencing decisions. The goal is to improve identification of high and low-risk offenders.

CONS

• Biased data: Since AI algorithms are trained on historical crime data, there is a danger of perpetuating and amplifying existing biases, as explained in “Garbage In, Garbage Out: The Dangers of Biased AI”. This could lead to over-policing of marginalized groups.
• Privacy erosion: As noted in “AI Surveillance: Security vs. Civil Liberties”, the data collection required by many AI systems infringes on privacy rights through pervasive monitoring and tracking. This threatens civil liberties.
• Poor transparency: The reasoning behind AI predictions is often opaque and difficult to understand, even for developers, due to the algorithms’ complexity. This lack of explainability reduces public trust and accountability, as examined in “Explainable AI: The Path to Ethical Algorithms”.
• Dehumanizing: Over-reliance on risk algorithms diminishes human discretion and nuanced decision-making in the criminal justice system, as discussed in “The Ethical Dilemma of AI Judges and Juries”. 

In summary, while AI offers promising capabilities to enhance public safety, we must carefully weigh the benefits against the risks to civil rights and liberties. As argued in previous SafeGrowth posts, policymakers should promote development of ethical AI systems with transparency, oversight, and impact evaluations to ensure AI prevents crime without infringing on human freedoms."

_______

YouTube with Kurt Bell, IT project manager from his AI presentation 

REAL PERSON, PLEASE

by Greg Saville 

I'm back  - the living, breathing, thinking, flesh and blood, me!

AI wrote the above SafeGrowth blog. Every word! I asked the artificial intelligence platform, claude by Anthropic, to write a 600-word blog on the role of AI in crime prevention. I asked it to reference prior blogs on this topic. I also asked it to frame the blog using the pros and cons.

The above text is the result. What do you think? What do I think? 

It did take considerable time for me to edit this. The basic prose was fine, but the fact-checking took a while. In short, it got some stuff wrong. 

Claude by Anthropic sums up some of the basic points nicely. I was encouraged it did not hide the truth of its own dangers like the erosion of civil liberties and privacy, poor transparency, and diminishing human discretion. These are not small matters and AI sees no reason to avoid the politics and critiques of itself. Not yet!

I was encouraged it cited some previous SafeGrowth blogs - but discouraged to realize they do not actually exist. With hundreds of blogs on this site, it is not surprising I cannot recall them all, but I do not remember any blogs with those topics. Neither did my search of the site find any. In other words, Claude made them up! That is disturbing, to say the least!

Claude by Anthropic uses the technical writing technique of bullet points. It avoids free-flowing prose or metaphors. It gets straight to the point because, I assume, it only had 600 words and it didn't have the time or expertise to construct a more poetic exposition. 

Bullet point writing, devoid of metaphor, simile, or literary license, can lead to a snooze fest. True, some of my paragraphs here could easily be rewritten into bullets, but reading through reams of bullet points is an exercise in ho-hum and humdrum. It is the humanness within writing that connects us to each other in ways not easily defined. AI seems to have problems with that - currently. 

Yet AI can write poetry and create art!

Ancient art masterpiece Sapphos, 470 BC. AI has made inroads into creating original poetry and painting - photo Wiki Creative Commons

AI lists predictive policing as a pro and sidesteps the ethical problems and critical research on predictive algorithms. AI does describe over-policing marginalized groups as a con, but it does not do so specifically so the reader does not connect the ethical problem with a specific application. Why?

It lists facial recognition software as a pro. But we know from research that AI facial recognition has fallen victim to the threat of false positives (mistakes) that have led to improper arrest and detention. There were prior blogs on this problem but claude.ai did not cite them even though I asked it to cite prior blogs. Instead, it cited blogs that were not terribly critical. 

The fact that AI cited some prior AI blogs (which do not exist on the SafeGrowth site) but did not cite others (more critical blogs) makes me wonder! Blogs from 2021 Summoning the Demon and AI vs CPTED, or this year's blog Stop Dave, I'm Afraid... all omitted! Why? I'm told the current AI chat platforms (ChatGPT, Claude, and others), cannot access real-time data on the internet. Maybe that's why?

PRIME TIME? 

This experiment in AI blogging does not convince me AI is ready for prime time. It still needs plenty of fact-checking and human review. Of course, that could be said of any editing process. The fact that it wrote the blog in technical jargon with bullets, and avoided any literary license, suggests AI has a ways to go to create interesting prose. 

Then again, IT project manager and author, Kurt Bell, tells us AI has already passed the famous Turing Test as of 2014. The Turing Test measures whether AI can be distinguished from a real human. In that test, at least, it could not. 

That should give us all pause, especially when it starts with "I’ll explore some key pros and cons". Who, I wonder, is it referring to when it says "I"?