Tuesday, October 31, 2023

Brazil & the Next Gen R/Evolution

Venue for the 2023 ICA CPTED Conference is Sao Paulo, Brazil. The largest city in the Americas has a metro population over 20 million - photo Wiki Creative Commons

by Gregory Saville

It’s Halloween today and the goblins and ghosts are looking for treats. An interesting ghost from my past appeared today, triggered by an international conference in Sao Paulo, Brazil this week. It all started 28 years ago…

In 1995 I ran an urban planning/criminology consultancy with my former business partner, Paul Wong in Vancouver, Canada. Our work in Crime Prevention Through Environmental Design (CPTED) had expanded across Canada and we were becoming alarmed at what we saw. The first CPTED publications were holistic, neighborhood-oriented, and they combined social programs with physical designs to cut crime opportunities. 

However the CPTED that we saw in some places was not holistic. It had de-evolved into target hardening, locks, and lights. There were very few guidelines and no certification programs. To our dismay, we discovered that the public, and municipalities across the world, had no clue about the failing quality control problems in CPTED. 


Basically, we located a like-minded CPTED practitioner, Barry Davidson from Calgary, Alberta, and in 1996 we launched the first-ever practitioner/researcher CPTED conference in Calgary. Thus was born the ICA - International CPTED Association - the first-ever global, non-profit, CPTED professional association. I have written a prior blog on the history of the ICA. 

With chapters all over the world, the ICA is the premiere global organization for professional CPTED in research and practice. Most recently, members of the ICA collaborated with others in the International Standards Organization to design and implement the first-ever, global CPTED standard, ISO 22341:2021 - “Guidelines for crime prevention through environmental design”. 

CPTED USA is the latest ICA chapter

The ICA has a talented and diverse board of directors from around the world and most recently, the ICA approved two new affiliate chapters – the CPTED USA and CPTED/PCAM Canada


This week the latest ICA conference - Safe Cities by People - is underway in Sao Paulo. I was unable to attend this year, but my colleagues Gerard Cleveland and Mateja Mihinjac will present a special session on the R/Evolution in 2nd and 3rd Generation CPTED. They will describe the latest advances and research in CPTED. Second Generation was launched in 1997 at the second-ever ICA conference in Orlando, Florida. Third Generation was launched by Mateja and myself 5 years ago at the ICA Conference in Cancun, Mexico. 

Most exciting is the announcement by Mateja and Gerard of two new publications. 

  • The first is a forthcoming book in 2024 by Mateja, Carl Bray, Jason Tudor, and myself, called Return to Walden.  That book presents the latest in the SafeGrowth method, to which this blog is dedicated. 
  • The second is Gerard and Annie Morrison’s new book Tier Teaching about better methods of teaching, learning, and safety in our schools, where the seeds of delinquency and dysfunction are planted, or removed, through competent education and educators. 

I am disappointed to miss this conference but to help Mateja and Gerard, I prepared a short video intro for their presentation today. Best wishes to all at the Sao Paulo ICA conference. 

Thursday, October 26, 2023

Whose voice speaks for us? Access control and the engagement trap

Residents take back their neighbourhood by access control of their roadways 

by Mateja Mihinjac

What happens when a community installs retractable pillars to block vehicular access into a neighbourhood of terraced blocks and local businesses? Access control is one of the fundamental principles of 1st Generation CPTED, established in 1972 by Oscar Newman in his book Defensible Space and employed judiciously by CPTED practitioners.

In one particular neighbourhood in my home city of Ljubljana, Slovenia, the issue of vehicle access control has been a contentious issue for several years. It regained interest a few weeks ago when a child was almost run over by a car while playing in a neighbourhood area intended for pedestrian use. Many have welcomed the installation of pillars, but others feel it a hasty decision lacking the preceding discussion. They seek more thoughtful consideration about the effects on senior residents, those with mobility issues, and the delivery of goods and services. 

No entry for private vehicles in the neighbourhood 


Soon after the installation of the pillars, emotional reactions appeared on the community Facebook group, as well as in local news, which reported reactions as “warm-cold”.

Some residents echoed sentiments such as “people would even drive directly to their apartment if they could” suggesting that people have become spoiled and accustomed to comfort. They welcomed the decision and praised the mayor for it.

Others maintained the move was made due to the nagging of a few who had the loudest voice but had no right to decide on behalf of the majority. They thought the right of access to their property was violated. They also reminded the “house rules” are already in place for each block. While these rules don’t seem to operate well in practice, it is clear the process of engagement was not managed well. 

Residents were not asked to partake in the discussion and they felt the decision was imposed on them. In SafeGrowth we are very familiar with this phenomenon and in our new forthcoming SafeGrowth book, we describe this as the engagement trap - listening to the loudest voices, consulting too late in the process, or insincere tokenism for political expedience.

Emergency vehicles waiting for access 


A few weeks later, the residents engaged in a more productive dialogue to try to find a solution that would suit the majority. The local government has also requested input and suggestions from the residents to find the most workable solutions.

Some suggestions have been implemented such as retracting the pillars for two hours during early morning hours for local business deliveries. The new decree also envisions special one-time access permits for house renovations or large item deliveries, or repair services since a number of residents have expressed concern about access. 

Now that the emotions have somewhat calmed down and the residents are starting to adjust to a new regime, many are calling for patience and cooperation in identifying the solutions. 

Some residents have even proposed this might be an opportunity for the introduction of new local businesses. For example, introducing a local delivery person(s) to assist with transporting goods from the surrounding shops either on foot or using micro-mobility options. Another example – expanding delivery lockers used by shipping services at the edge of the suburbs since they are now unable to deliver goods to people’s doorstep. 

Local government has already introduced “Kavalir”, a small electric golf-cart-like vehicle that drives between the neighbourhood and adjacent produce market on a daily basis. This service is free of charge and primarily intended for those with mobility issues.

Terraced residences included narrow pedestrian corridors intended for pedestrians, not vehicles 


It is commendable that the municipality responded so quickly to address this local problem, but it is discouraging to see how frequently decision-makers fail to initiate effective discourse with the local residents until complaints arise. 

The inability to engage residents, or the use of the engagement trap to substitute for authentic engagement, leads to more problems and confusion. All of that can be avoided from the start of the process with authentic communication. Time will tell if this is yet just another attempt at tokenism or a lesson in civic engagement. 

Saturday, October 14, 2023

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.


  • 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.


  • 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 


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?


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"?