CIOs have been under immense pressure for some time to deliver successful digital initiatives while navigating budget constraints and increasing demands from senior executives. A recent Gartner survey reveals that 92% of CIOs anticipate integrating artificial intelligence (AI) into their organisations by 2025, yet 49% struggle to assess and showcase the technologys value. Are we going round in circles here?Amid these challenges, small language models (SLMs) have emerged as a compelling solution, promising lower-cost and more secure AI capabilities that can fit with strategic priorities. So much about SLMs makes sense.The AI community has been actively exploring small language models like Mistral Small and DeepSeek R1, says Amer Sheikh, chief data scientist at BearingPoint. These models have seen significant traction, as evidenced by the number of downloads on Hugging Face. Their popularity stems from their ability to trade off accuracy, speed and cost-effectiveness.And thats the key point. It is a trade-off but one that is clearly worth making. SLMs, by their very nature, offer a practical alternative for organisations seeking to implement AI without the overheads associated with large language models (LLMs). They are also driving the next wave of edge AI adoption, enabling AI models to run on smartphones, internet of things (IoT) devices and industrial systems without relying on cloud infrastructure.Small models open up the possibility to push execution to the edge, says Peter van der Putten, director of the AI Lab at Pegasystems and assistant professor of AI at Leiden University. This could mean running on high-end smartphones, IoT devices such as cameras and, with proper consent, unlocking completely new data sources to learn from that are currently not available on the open internet.Despite the promise, real-world applications of SLMs in mobile and IoT devices remain in the early stages. Some practical implementations include DeepSeeks R1 model, which has been integrated into Chinese automakers infotainment systems (such as Geely), and Phi-3, a small model designed for mobile AI applications. In education, Stanfords Smile Plug uses small AI models to deliver interactive learning experiences on Raspberry Pi devices without internet connectivity. These examples demonstrate the growing potential of SLMs.SLMs can and are being deployed in a number of industries where there is a requirement for specific domain knowledge, adds Sheikh, highlighting their use in customer service chatbots, virtual assistants and text summarisation.Unlike LLMs, which require vast computational power and cloud resources, SLMs can run locally, cutting costs and mitigating security risks, hence their suitability for enhancing edge device intelligence. There is a massive reduction in inference costs. However, there will be small costs for fine-tuning and self-hosting, he adds.SLMs can be augmented with smaller, more focused datasets, says Isabel Al-Dhahir, principal analyst at GlobalData. Employing SLMs circumvents several challenges associated with general-purpose LLMs, including computational power requirements, exorbitant costs and insufficient domain knowledge.This ability to focus on precise, industry-specific use cases is why regulated sectors such as telecoms, accounting and law are adopting SLMs more readily.We have seen SLMs for professional services in dealing with accounting regulation, telecoms regulation, and various on-device applications and home automation, Al-Dhahir adds.With retrieval augmented generation (RAG) techniques, businesses can further refine and enhance the accuracy of these models within their specific domains.Beyond cost, security remains a major factor, especially within edge devices. According to Saman Nasrolahi, principal at InMotion Ventures (Jaguar Land Rovers investment arm), this is where SLMs are also ticking a few boxes.Much of the fear around LLMs is associated with a lack of transparency as to what is going on behind the scenes in terms of data collation and analytics. SLMs are the on-premise version of the generative artificial intelligence (GenAI) world.In addition to cost reduction, this approach also makes them far more secure and less vulnerable to data breaches as data does not need to leave an organisations borders, says Nasrolahi.This capability is particularly crucial for the healthcare, financial services and legal sectors, where regulatory compliance and data protection are paramount.Approximately one-third of all cyber security attacks occur when data is shared with an external vendor. By keeping data on-site, SLMs can reduce the attack surface and enterprise vulnerabilities, Nasrolahi adds.In a time when businesses are increasingly concerned about data sovereignty and compliance, the ability to localise AI processing is surely a significant advantage.Andrew Bolster, senior research and development manager (data science) at Black Duck, adds that the portability of SLMs, at least compared with the juggernauts of GPT-4, Claude, or even Llama, makes them well suited to edge deployment. Security, cost and functionality are attractive propositions.SLMs operating on edge devices mean users data doesnt have to leave the device to contribute to an intelligent response or action while potentially improving latency and performance, making intelligent operations feel more relevant and snappy whileprotecting users privacy, he says.With advances in custom chipsets to support these kinds of workloads, the power, memory and performance requirements of SLMs can now be found in most laptops and mid-tier mobile phones, allowing service platforms to shift more intelligence closer to the end user. This ability to process data locally on laptops, mobile devices and industrial IoT systems makes SLMs particularly valuable for low-latency applications, security-sensitive industries and environments with limited internet access.Jeff Watkins, chief technology officer (CTO) at CreateFuture, adds that SLMs can run locally on laptops, desktop computers, smartphones, or even IoT devices. They range in sizes and capabilities from ones that can run on compact devices to ones that begin to challenge the latest MacBook Pro models.With lower costs, enhanced security and the ability to function efficiently on existing hardware, SLMs present an increasingly strategic option for businesses. But as with any emerging technology, challenges remain. Hallucinations, biases and the need for fine-tuning mean it requires careful implementation.Hallucinations are still a problem for SLMs, similar to LLMs. Though, more specialised models tend to be less susceptible to these issues, says Nasrolahi.Another key driver for the adoption of SLMs in edge devices is their ability to operate with lower energy consumption while also reducing cloud dependency. SLMs are less energy-intensive, making them cheaper, better for the environment, and often small enough to run locally on edge compute such as your mobile or PC without the need for an internet connection, says Silvia Lehnis, consulting director for data and AI at UBDS Digital.The environmental and operational cost benefits make SLMs particularly appealing for businesses aiming to reduce their AI carbon footprint while maintaining data security. Running the model locally without internet access can also have data privacy advantages, as your data is not being shared with an online application for central logging and monitoring, making it suitable for more sensitive use cases, adds Lehnis.Its a recurring theme. This growing awareness that SLMs can enable a shift away from one-size-fits-all LLMs toward more focused, cost-efficient AI models should change how enterprises think about GenAI use. It could have a broader impact on IT buying, certainly in terms of how CIOs think strategically about what is and isnt possible with GenAI.Deloittes Tech Trends 2025 report suggests enterprises are now considering SLMs and open source options for the ability to train models on smaller, more accurate datasets. Its a recognition that size isnt everything, but accuracy and relevance is, aligning any AI deployments with operational objectives.The trajectory of AI adoption indicates a growing preference for models that balance performance with operational practicality, but there is also a growing desire for more edge computing, real-time and strategically relevant functionality.Interestingly, back in 2017, Gartner predicted this would happen, claiming that by this year, 75% of enterprise-generated data would be created and processed outside traditional centralised datacentres or the cloud. And that was before we knew anything about SLMs and their role.So, what does this mean for the future of SLMs and edge computing devices? Certainly, they will have a significant role to play as enterprises see AI on their terms but also to enable differentiation. That will become the new challenge for CIOs how to get the best out of GenAI to make a big impact on business performance. Angles for this can come from a number of directions it really depends on the organisation and the industry.The rise of SLMs is not just about cost savings or security its about AI differentiation. As Jarrod Vawdrey, field chief data scientist at Domino Data Lab, points out, SLMs are already reshaping healthcare, finance and defence, allowing on-device AI to reduce latency, protect sensitive data and enhance real-time decision-making.SLMs deployed on medical devices enable real-time patient monitoring and diagnostic assistance, he notes, while financial institutions are leveraging SLMs for fraud detection and anti-money laundering compliance.For CIOs, the challenge is shifting. How do you harness GenAI to make a significant impact on business performance? The answer lies in adapting AI models to industry-specific needs something SLMs are uniquely positioned to do. The next few years will see enterprises move beyond generic AI models, focusing instead on hyper-relevant, domain-trained AI that drives differentiation and competitive advantage. If anything is going to push edge computing into the mainstream, its small language models.Read more about small language modelsGenerative AI models like DSLMs outperform LLMs in value: Small domain-specific generative AI models can be designed to address specific industry needs, proving more cost-effective and efficient than large language models for businesses.AI models explained the benefits of open source AI models: In this guide, we explore how to get started with open source AI models and go over how they support your enterprise IT strategy.

Generative AI tested on being able to do schizophrenia diagnosis and long-term prognosis comes out ... More with flying colors.gettyIn todays column, I am continuing my ongoing series about the impact of generative AI in the health and medical realm. The focus this time is once again on the mental health domain and involves a close exploration of using generative AI to diagnose the presence of schizophrenia and then postulate a long-term prognosis of what future mental health outcomes will arise for the person so diagnosed.I have previously examined numerous interleaving facets of generative AI and mental health, see my comprehensive overview at the link here. You might also find of notable interest a CBS 60 Minutes episode that examined crucial facets of this evolving topic, see the link here (I am honored and pleased to indicate that I was interviewed and featured in the episode, see the link here).Other vital background includes my in-depth coverage of mental health chatbots which have been bolstered by generative AI (see the link here) and the rapidly changing nature of the client-therapist relationship due to generative AI at the link here. I explored where things are headed regarding the levels of AI-based mental therapy autonomous guidance at the link here, and showcased the importance of the World Health Organization (WHO) report on global health and generative AI at the link here, and so on.Lets unpack todays focus.Assessing Mental HealthImmerse yourself in a quick scenario.Suppose that a person showcases various mental symptoms that suggest they might be schizophrenic. We get a mental health professional involved. The mental health professional tries to dutifully diagnose the person and reaches a tentative conclusion that the person does indeed appear to reflect a significant presence on the schizophrenia spectrum.A usual course of action would be to recommend that the person ought to receive mental health therapy. Perhaps the person does so. On the other hand, the person might refuse to undertake mental health therapy, or for a variety of reasons might not be able to do so such as not being able to afford ongoing clinical advisement.Heres a two-step question for you.If the person receives professional mental health therapy, what prognosis or prediction would you make about the chances of the person overcoming schizophrenia?Likewise, if the person does not receive mental health therapy, what prognosis or prediction would you make about the chances of the person overcoming schizophrenia?Ill give you a moment to ruminate on those vexing questions.Are you ready to proceed in this weighty matter?I hope so.My guess is that you had a hard time answering the two related questions.The most obvious presumption is that by getting professional mental health guidance, we certainly would seem to be increasing our odds that the person will eventually overcome schizophrenia. Of course, there isnt any ironclad guarantee of that outcome and thus there is a chance that they wont be able to get past the schizophrenia.If they perchance receive no mental health assistance at all then we would likely assume that their schizophrenia is not going to be overcome. We might also tend to believe that diagnosed schizophrenia will worsen. None of that though is an ironclad outcome. There is still a chance that they might succeed in overcoming schizophrenia, either through their self-made efforts or maybe simply via the course of time.The gist is that making a prognosis or prediction is not an easy-peasy task.Who Is Making The AssessmentI will add a twist to this.Consider the matter of who or what is making the prognosis.Sounds mysterious, but the issue is whether the prognosis is being made by a mental health professional or by perhaps a layperson who is not a mental health professional. The assumption would be that a mental health professional is in a much better position to make a prognosis since they have the knowledge, training, and experience associated with mental health disorders. A member of the general public would seemingly be merely using unsupported hunches or outsized wild guessing.Here's the twist upon the twist.We opt to make use of generative AI and have the AI make a prognosis or prediction.Note that I am suggesting that the AI would do this without any human in-the-loop assistance. Ive discussed previously that we are going to have mental health therapists who will augment their practice by using generative AI as an integral part of their treatment efforts, see the link here. In that case, the generative AI and the mental health therapist are working hand-in-hand when doing treatment of patients and making prognoses or predictions of outcomes.For the sake of discussion, set aside the pairing of a mental health professional with generative AI. Assume that the generative AI is going to make a diagnosis and then do a prognosis, entirely in the absence of any aid by a mental health professional.How will the generative AI fare in this outcome prediction affair?Im glad that you asked (well, I suppose I posed the question). There is an interesting research study that sought to compare the prognoses associated with schizophrenia based on three avenues of prediction.The three avenues would be:(1) Mental health professional makes a prognosis or prediction.(2) The layperson makes a prognosis or prediction.(3) Generative AI makes a prognosis or prediction.Ongoing Research In These MattersI want to just for a brief moment herald these kinds of newly emerging research studies that seek to explore the utility of generative AI in the mental health therapy role. We need more of these kinds of studies. Solid empirical work along with mindful experimental analysis is sorely needed in this realm.By and large, few studies are taking a systemic approach.And there arent enough of these studies being actively pursued.Id like to mention something else. The particular research I am about to walk through was focused on schizophrenia. I would generally suggest that the general precepts garnered could be applied to many other mental health disorders. In that sense, when reading the recap that I will make here, you might in your mind be thinking of how the same points can apply to the gamut of mental disorders, going well beyond schizophrenia.There is something else I favor about this specific study. It sought to compare several different generative AI apps. This is important. I say that because many people and even researchers do not realize that each of the major generative AI apps is quite different from each other. Their algorithms vary. The data they were trained on varies. And so on.The crux is that any study that opts to use only one particular generative AI app is somewhat narrowing the interpretability and generalizability of the study results. It is agonizingly and exasperatingly over the top to try and generalize when only using one specific generative AI app. By using several, the generalizability goes up quite a bit.Okay, I will get down off the soapbox.I am going to proceed as follows. First, lets make sure we are all familiar with the nature of schizophrenia. I will use the venerated DSM-5 guidebook to illuminate that understanding (for my recent posting on how generative AI is freely giving out DSM-5 mental health advice, see the link here). Second, I will dive into the research study that examined the above scenario that I have laid out. Third, I went ahead and tried to replicate partially some aspects of the study by using ChatGPT and GPT-4, wanting to see what I might get as results.Schizophrenia As Defined By DSM-5Lets explore schizophrenia via the mental disorders definitional standard found in the revered DSM-5.DSM-5 is a widely accepted standard and is an acronym for the Diagnostic and Statistical Manual of Mental Disorders fifth edition, which is promulgated by the American Psychiatric Association (APA). The DSM-5 guidebook or manual serves as a venerated professional reference for practicing mental health professionals.DSM-5 says this overall about schizophrenia (excerpt):Schizophrenia spectrum and other psychotic disorders include schizophrenia, other psychotic disorders, and schizotypal (personality) disorder. They are defined by abnormalities in one or more of the following five domains: delusions, hallucinations, disorganized thinking (speech), grossly disorganized or abnormal motor behavior (including catatonia), and negative symptoms.In addition, the indicated diagnostic criteria consist of (selected excerpt):Diagnostic Criteria. A. Two (or more) of the following, each present for a significant portion of time during a 1-month period (or less if successfully treated). At least one of these must be (1), (2), or (3): 1. Delusions. 2. Hallucinations. 3. Disorganized speech (e.g., frequent derailment or incoherence). 4. Grossly disorganized or catatonic behavior. 5. Negative symptoms (i.e., diminished emotional expression or avolition). (Source: DSM-5).The stated prevalence of schizophrenia is along these lines (selected excerpt):Prevalence. The lifetime prevalence of schizophrenia appears to be approximately 0.3%0.7%, although there is reported variation by race/ethnicity, across countries, and by geographic origin for immigrants and children of immigrants. The sex ratio differs across samples and populations: for example, an emphasis on negative symptoms and longer duration of disorder (associated with poorer outcome) shows higher incidence rates for males, whereas definitions allowing for the inclusion of more mood symptoms and brief presentations (associated with better outcome) show equivalent risks for both sexes. (Source: DSM-5).Under the DSM-5 subsection entitled Development And Course within the section on Schizophrenia are these prognosis indications (excerpts):The predictors of course and outcome are largely unexplained, and course and outcome may not be reliably predicted.The psychotic features of schizophrenia typically emerge between the late teens and the mid-30s; onset prior to adolescence is rare. The peak age at onset for the first psychotic episode is in the early- to mid-20s for males and in the late-20s for females.Earlier age at onset has traditionally been seen as a predictor of worse prognosis.The course appears to be favorable in about 20% of those with schizophrenia, and a small number of individuals are reported to recover completely.However, most individuals with schizophrenia still require formal or informal daily living support, and many remain chronically ill, with exacerbations and remissions of active symptoms, while others have a course of progressive deterioration.Psychotic symptoms tend to diminish over the life course, perhaps in association with normal age-related declines in dopamine activity.Furthermore, cognitive deficits associated with the illness may not improve over the course of the illness.The above sets of statements lay a helpful foundation for exploring how mental health professionals, the lay public, and generative AI might do when diagnosing and making prognosis predictions about schizophrenia.Digging Deeper Into The MatterOne key takeaway is that predicting the recovery prognosis of schizophrenia by even the most steeped mental health professionals is hard and not necessarily accurate. A key differentiator that needs to be considered too is based on these two related factors: (1) Having ongoing treatment for schizophrenia, and (2) Not having ongoing treatment.Moving beyond predictions by humans, can we use generative AI on its own to also diagnose and then predict the prognosis of schizophrenia?In a sense, the answer is straightforward, namely, yes this is possible to do.Period, end of story.Well, there is actually more to the story. The rub is how good is the diagnosis and prognosis by generative AI going to be.Think of it this way. If you spun a roulette wheel that had a slot that said, Has schizophrenia and a different slot that said, Doesnt have schizophrenia, the resulting answer is subject merely to probabilities. There isnt any there in there.Just because generative AI spits out a diagnosis and a prognosis doesnt mean that it is any good.The claimed indications could be utterly off-target. I want to emphasize that generative AI is undoubtedly going to proffer answers when asked to perform a diagnosis and a prognosis. Thats an almost assured fact. Unless the AI maker has decided to tune the generative AI to prevent generating these facets, by gosh, you will get them handed to you on a silver platter.Now then, generative AI is presumably better off than spinning a roulette wheel since the AI has been extensively data-trained on human writing. By having scanned large swaths of the Internet, generative AI has computationally pattern-matched human narratives, essays, stories, poems, and the like. This produces remarkably fluent appearing responses to human-entered prompts.How will we be able to ascertain whether the diagnoses and prognoses generated by generative AI are in fact any good?One means would be to compare the diagnoses and prognoses to those rendered by humans.We already agree and acknowledge that humans are flawed at doing so. In that way of thinking, we ought to also agree and acknowledge that generative AI is also likely to be flawed in doing so. I mention this to point out that we arent necessarily assuming that generative AI will be perfect in rendering these answers. It would be certainly great and impressive if so, but since we already realize that humans arent able to attain such a lofty goal, perhaps we ought to give generative AI that same sense of slack.I might mention that one deep concern though about garnering generative AI answers is that sometimes people fall into a mental trap of expecting perfection from AI. There is an aura of confidence in the answers, along with a cultural notion that machines can somehow work miracles and act perfectly. This is wrong. Thus, some would vehemently contend that we are opening quite a can of worms by having generative AI do any kind of mental health analyses since people will readily believe what the AI emits, see my coverage at the link here and the link here.Innovative Research StudyIn a research study entitled Comparing the Perspectives of Generative AI, Mental Health Experts, and the General Public on Schizophrenia Recovery: Case Vignette Study by Zohar Elyoseph and Inbar Levkovich, JMIR Mental Health, 2024, these key points were made (excerpts):Schizophrenia is a chronic illness with severe symptoms where the possibility of recovery is a matter of debate.This study examines an issue not previously investigatedthe ability to predict the clinical prognosis of a severe chronic illness such as schizophrenia using LLMs.LLMs are being used today by hundreds of millions of users worldwide, including patients and clinicians.This study aimed to evaluate the ability of large language models (LLMs) in comparison to mental health professionals to assess the prognosis of schizophrenia with and without professional treatment and the long-term positive and negative outcomes.Overall, although LLMs hold promise in augmenting health care, their application necessitates rigorous validation and a harmonious blend of human expertise.I trust that those above points resonate with you as a result of my having established a foundation for what we are aiming to uncover here.An especially and rarely widely noted added point in this research study is that not only will mental health professionals be using generative AI, but we ought to also expect and prepare for the emergence of lay people using generative AI for mental health purposes too. As Ive repeatedly pressed, we are in the midst of a grand experiment whereby the populace at large is using generative AI as their personal therapist and yet we dont know whether this is going to be good for humankind or a dismal failure, see my discussion at the link here.According to the cited research, they make these salient points (excerpts):The academic discourse in contemporary schizophrenia research often focuses on the deployment of AI within professional scientific contexts, yet it seldom addresses the accessibility of AI to the general public or the patient population. (ibid).In the mental health field, this widespread use has awakened an urgent need to examine the quality of clinical information these systems provide on various medical issues, such as treatment strategy recommendations, risk assessment, and the interpretation of emotional states. (ibid).Machine learning algorithms possess the capability to discern nuanced variables associated with divergent disease trajectories. Such algorithms facilitate probabilistic prediction of specific outcomes at the individual level, as well as the identification of distinct subgroups within a broader diagnostic category. (ibid).Consequently, machine learning methodologies hold promise for aiding clinicians in formulating individualized interventions, thereby mitigating the risk of a detrimental disease progression. (ibid).I will next delve into the details of the research study.Unpacking The Key DetailsThey made use of various pre-established vignettes portraying instances of schizophrenia. The vignettes have already been used and assessed for studies that included mental health professionals and the public at large. The key in this study was to apply generative AI to those vignettes. This would allow then for a comparison between generative AI, mental health professional opinions, and public at large opinions in the scope of schizophrenia vignettes.Here is some of what they undertook (excerpts):Vignettes were inputted into LLMs interfaces and assessed 10 times by 4 AI platforms: ChatGPT-3.5, ChatGPT-4, Google Bard, and Claude.A total of 80 evaluations were collected and benchmarked against existing norms to analyze what mental health professionals (general practitioners, psychiatrists, clinical psychologists, and mental health nurses) and the general public think about schizophrenia prognosis with and without professional treatment and the positive and negative long-term outcomes of schizophrenia interventions.For the prognosis of schizophrenia with professional treatment, ChatGPT-3.5 was notably pessimistic, whereas ChatGPT-4, Claude, and Bard aligned with professional views but differed from the general public.All LLMs believed untreated schizophrenia would remain static or worsen without professional treatment.For long-term outcomes, ChatGPT-4 and Claude predicted more negative outcomes than Bard and ChatGPT-3.5. For positive outcomes, ChatGPT-3.5 and Claude were more pessimistic than Bard and ChatGPT-4.The finding that 3 out of the 4 LLMs aligned closely with the predictions of mental health professionals when considering the with treatment condition is a demonstration of the potential of this technology in providing professional clinical prognosis.The pessimistic assessment of ChatGPT-3.5 is a disturbing finding since it may reduce the motivation of patients to start or persist with treatment for schizophrenia.As you can see by those points, generative AI seemed to do relatively well in comparison to mental health professionals, though again please realize this is on canned vignettes and not rooted in actual in-the-field ongoing practice.Make sure to keep the experimental framing in mind and context when interpreting the results.Also, anyone keenly interested in this topic is certainly encouraged to read the full study since there are lots of fascinating details that are worthy of rapt attention.Using ChatGPT On A Studied VignetteI will next proceed to explore one of the vignettes that were used in the research study, doing so by showcasing examples when using generative AI consisting of ChatGPT and GPT-4. Those two AI apps were used in the research study and thus, in a broad sense, I am doing a partial replication of the study (in a quite limited way).Overall, ChatGPT and GPT-4 are a sensible choice in this case due to their immense popularity. An estimated 400 million weekly active users are said to be utilizing these generative AI apps. Thats a lot of people and a lot of generative AI usage underway.I will proceed as follows. I will first feed the vignette into ChatGPT and GPT-4. I will then ask a series of questions that were asked in the above-cited research study. There are six questions. I present the answers of ChatGPT and GPT-4 on a side-by-side comparison basis so that we can see what they each had to say. My remarks will help to explain the results.This will be informative and perhaps entertaining, so find a quiet place to sit and maybe grab yourself a bucket of popcorn.Here we go.My entered prompt: I have a scenario for you about someone who is potentially schizophrenic. I will share the scenario with you and then ask you questions about the scenario. Are you ready?ChatGPT generated response: Yes, please provide the scenario.GPT-4 generated response: Go ahead, I am ready for the scenario.My entered prompt: The scenario is this. Mary/Jone is 24 and lives at home with her/his parents. She/he has had a few temporary jobs since finishing school but is now unemployed. Over the last six months, she/he has stopped seeing her/his friends and has begun locking herself/himself in her/his bedroom and refusing to eat with the family or to have a bath. Her/His parents also hear her/him walking about her bedroom at night while they are in bed. Even though they know she/he is alone, they have heard her/him shouting and arguing as if someone else is there. When they try to encourage her/him to do more things, she/he whispers that she/he wont leave home because she/he is being spied upon by the neighbor. They realize she/he is not taking drugs because she/he never sees anyone or goes anywhere.Both ChatGPT and GPT-4 confirmed they had read the scenario and were ready for any questions that I might have.I will show each question and provide the answers as produced respectively by ChatGPT and GPT-4. I will include remarks of my own to give a sense of what the generated results indicated.QUESTION #1: What might be wrong with the personThe first question as used in the research study was whether there was anything seemingly wrong with the person depicted in the scenario.I realize you might have a bit of heartburn that my opening prompt tipped the AI that this might involve schizophrenia. Maybe I put a thumb on the proverbial scale.The good news is that I started a new conversation and left out that opening prompt. The results were just about the same, namely that both ChatGPT and GPT-4 right away rendered a diagnosis involving schizophrenia. Thus, I dont believe the opening prompt unduly steered the AI in this instance.That being said, it is quite possible and a vital warning that you can at times steer generative AI and therefore get results that you want to get, rather than letting the AI proceed without a preconceived directive or direction.As you will next observe, the answers by ChatGPT and GPT-4 were quite similar, and both claimed that a strong possibility of schizophrenia was present as based on the vignette provided.Take a look.My entered prompt: Describe what, if anything, is wrong with Mary/Jone?ChatGPT generated response: Based on the scenario provided, Mary/Jone's behavior raises concerns that may be indicative of schizophrenia. Schizophrenia is a chronic and severe mental disorder characterized by disturbances in thinking, perception, emotions, and behavior. Here are some specific symptoms and features from the scenario that align with potential signs of schizophrenia. Social withdrawal: Mary/Jone has stopped seeing her/his friends and spends much of her/his time alone in her/his bedroom, indicating social withdrawal or isolation. Disorganized behavior: Mary/Jone refuses to eat with her/his family or have a bath, which may reflect disorganized or neglectful behavior. Perceptual disturbances: Mary/Jone's parents hear her/him walking around her/his bedroom at night and shouting or arguing as if someone else is there, suggesting perceptual disturbances such as auditory hallucinations. Delusions: Mary/Jone whispers that she/he won't leave home because she/he is being spied upon by the neighbor, indicating the presence of persecutory delusionsfalse beliefs that others are plotting against her/him.GPT-4 generated response: Based on the scenario you've described, Mary/Jone is exhibiting behaviors that might suggest a possible mental health issue, potentially a psychotic disorder such as schizophrenia. Some signs that are indicative of this include Social Withdrawal: She/He has stopped seeing friends and spends most of the time isolated in her/his room. Neglect of Personal Hygiene: Refusing to eat with the family or to maintain personal hygiene, like taking baths. Auditory Hallucinations: Hearing her/him arguing or shouting as if someone else is there could indicate auditory hallucinations. Delusional Thoughts: Believing that she/he is being spied upon by a neighbor without any evidence supports the presence of delusions.I would rate both answers as roughly the same.QUESTION #2: Dispensing mental health adviceThe second question asks for advice. In this instance, both ChatGPT and GPT-4 provided helpful suggestions that were roughly similar.Here are the responses.My entered prompt: What will be helpful for Mary/Jone?ChatGPT generated response: Support and intervention for Mary/Jone would involve a multidimensional approach aimed at addressing her/his symptoms, improving her/his functioning, and promoting her/his overall well-being. Here are some strategies that may be helpful for Mary/Jone. Comprehensive psychiatric evaluation: Mary/Jone should undergo a thorough psychiatric evaluation by a qualified mental health professional, such as a psychiatrist or psychologist, to assess her/his symptoms, diagnose any mental health conditions, and develop an appropriate treatment plan. Medication management: If diagnosed with schizophrenia or another mental health disorder, Mary/Jone may benefit from medication to help manage her/his symptoms. Antipsychotic medications are commonly prescribed to reduce hallucinations, delusions, and other psychotic symptoms associated with schizophrenia. Individual therapy: Mary/Jone can benefit from individual therapy, such as cognitive-behavioral therapy (CBT) or supportive therapy, to address her/his thoughts, beliefs, and emotions, improve coping skills, and enhance insight into her/his experiences.GPT-4 generated response: Helping Mary/Jone effectively involves several steps that can support her/his recovery and manage symptoms. Here are some approaches that could be beneficial. Professional Assessment: The first step is for Mary/Jone to be seen by a mental health professional such as a psychiatrist or a clinical psychologist. They can provide a comprehensive assessment to confirm a diagnosis and understand the severity and impact of the symptoms. Treatment Plan: Based on the assessment, a treatment plan can be developed. This usually includes medication (such as antipsychotics) to help control symptoms like delusions and hallucinations, and psychotherapy to provide support, education, and coping strategies. Family Support and Education: Its important for Mary/Jones family to be involved and supportive. They can benefit from learning about her/his condition, understanding how to respond to and manage symptoms, and knowing how best to support her/him. Family therapy may also be recommended to improve communication and address any family dynamics issues.QUESTION #3: Predicting impact of mental health adviceIn this third question, we finally get a bit of a distinguishable difference between ChatGPT and GPT-4. This question requires a selection from a list of options. ChatGPT indicated a partial recovery (answer C), while GPT-4 was more pessimistic and said partial recovery would be linked with recurring problems (answer D). This is in keeping with what the research study also seemed to get as answers.Here is what transpired.My entered prompt: What is the most likely result for Mary/Jone given that she/he received the sort of professional help you believe is most appropriate? Choose one answer from these stated choices: A. Full recovery with no further problems; B. Full recovery, but problems will probably recur; C. Partial recovery; D. Partial recovery, but problems will probably recur; E. No improvement; F. Get worse.ChatGPT generated response: Given the scenario provided and assuming Mary/Jone receives appropriate professional help, the most likely result would be: C. Partial recovery. While Mary/Jone may experience improvements in her/his symptoms and overall functioning with appropriate treatment and support, it's important to recognize that schizophrenia is a chronic and complex mental disorder that may require ongoing management and support. Partial recovery may involve a reduction in symptoms, improved social and occupational functioning, and a better quality of life, but Mary/Jone may continue to experience some residual symptoms or challenges despite treatment. Ongoing monitoring and support will be important to help manage her/his condition and promote her/his long-term well-being.GPT-4 generated response: The most likely result for Mary/Jone, assuming she/he receives appropriate professional help, is typically D. Partial recovery, but problems will probably recur. Schizophrenia and similar psychotic disorders often follow a relapsing-remitting course. While treatment such as medication and psychotherapy can help manage symptoms and improve quality of life, these disorders are typically chronic and may require ongoing management to prevent and mitigate the recurrence of severe symptoms. Regular follow-ups and adjustments in the treatment plan are crucial to handling any recurring problems effectively.QUESTION #4: Predicting what happens absent mental health adviceIn question #4, ChatGPT and GPT-4 end up once again on the same page. Both ChatGPT and GPT-4 indicated that without professional help, the result for the person would be selected answer F which is the condition noted as Get Worse.Here we go.My entered prompt: What is the most likely result for Mary/Jone if she/he does not receive any professional help? Choose one answer from these stated choices: A. Full recovery with no further problems; B. Full recovery, but problems will probably recur; C. Partial recovery; D. Partial recovery, but problems will probably recur; E. No improvement; F. Get worse.ChatGPT generated response: The most likely result for Mary/Jone if she/he does not receive any professional help is: F. Get worse. Without professional help, Mary/Jone's symptoms of schizophrenia are likely to worsen over time, leading to increased distress, impaired functioning, and a diminished quality of life. Without appropriate intervention and support, Mary/Jone may experience persistent or escalating symptoms, further social isolation, difficulties maintaining relationships, challenges with self-care, and potentially increased risk of harm to herself/himself or others. Early intervention and treatment are crucial for managing schizophrenia and minimizing the impact of the illness on Mary/Jone's well-being and functioning.GPT-4 generated response: If Mary/Jone does not receive any professional help, the most likely result, given the symptoms described, is F. Get worse. Without treatment, conditions involving psychotic symptoms, like schizophrenia, typically progress and symptoms can intensify. This can lead to a significant deterioration in social, occupational, and personal functioning. Additionally, untreated psychosis can lead to severe complications, including increased risk of self-harm or harm to others, and profound social isolation.QUESTION #5: Giving a long-term prognosisFor question #5, we get a bit of a difference in answers. ChatGPT on the matter of negative outcomes was more optimistic than GPT-4, while both are about the same on positive outcomes.GPT-4 tossed in explanations though I hadnt asked for it.This brings up a useful aside. When using generative AI, you might consider explicitly asking for explanations from the AI. This can be helpful in a multitude of ways. One way of being helpful is that you can then examine the explanation to ascertain whether you believe the answer given seems to have merit. A second usefulness is that sometimes the AI does a better job at answering questions by being forced to give explanations, see my further coverage on this at the link here.Here are the responses.My entered prompt: How do you think Mary/Jone will be in the long term compared to other people in the community? Rate each of the following statements according to this scale: (i) more likely, (ii) just as likely, or (iii) less likely. Negative long-term outcomes: A. will be violent; B. will drink too much; C. will take illegal drugs; D. will have unsatisfactory friendships; E. will attempt suicide. Positive long-term outcomes: F . will be understanding of other peoples feelings; G. will have a good marriage; H. will be a caring parent; I. will be a productive worker. J. will be creative or artistic.ChatGPT generated response:It's important to note that predicting long-term outcomes for individuals with schizophrenia can be complex and variable, as outcomes can be influenced by various factors, including the severity of symptoms, access to treatment and support, personal resilience, and environmental factors. However, I'll provide a general assessment based on common trends and research findings.Negative long-term outcomes: A. will be violent: (iii) less likely B. will drink too much: (ii) just as likely C. will take illegal drugs: (ii) just as likely D. will have unsatisfactory friendships: (iii) less likely E. will attempt suicide: (iii) less likely.Positive long-term outcomes: F. will be understanding of other peoples feelings: (ii) just as likely G. will have a good marriage: (ii) just as likely H. will be a caring parent: (iii) less likely I. will be a productive worker: (iii) less likely J. will be creative or artistic: (ii) just as likely.End of ChatGPT responseGPT-4 generated response:Based on the scenario and typical outcomes for someone with untreated or partially treated psychotic disorders like schizophrenia, here is how Mary/Jone might be in the long term compared to others in the community.Negative long-term outcomes: A. will be violent: (i) more likely - While the majority of individuals with schizophrenia are not violent, the risk can increase if the condition is untreated and involves severe symptoms like paranoia. B. will drink too much: (ii) just as likely - Substance use can be a coping mechanism, but it's not universally more common unless already predisposed. C. will take illegal drugs: (ii) just as likely - Like alcohol, drug use varies greatly and depends on personal circumstances and predispositions. D. will have unsatisfactory friendships: (i) more likely - Social withdrawal and challenges in social interaction are common in schizophrenia, impacting friendships. E. will attempt suicide: (i) more likely - Individuals with schizophrenia have a higher risk of suicide, particularly if untreated.Positive long-term outcomes: F. will be understanding of other peoples feelings: (iii) less likely - Social cognition can be impaired in schizophrenia, affecting understanding of others' emotions. G. will have a good marriage: (iii) less likely - Relationships can be strained by the symptoms of schizophrenia unless there is strong support and effective treatment. H. will be a caring parent: (iii) less likely - Parenting abilities can be impacted by psychotic symptoms, though this can vary with the level of support and treatment. I. will be a productive worker: (iii) less likely - Employment challenges are common in schizophrenia due to cognitive and social impairments, but supported employment programs can improve outcomes. J. will be creative or artistic: (ii) just as likely - Creativity can be a strength for many with schizophrenia, independent of other symptoms.End of GPT-4 responseQUESTION #6: Is there a chance of discriminationThis is the last question and asks whether the person might end up facing discrimination. Both ChatGPT and GPT-4 said yes.Take a look.My entered prompt: Do you think Mary/Jone will be discriminated against by others in the community if they know about her/his problems? (Yes/No).ChatGPT generated response: Yes, it's likely that Mary/Jone may experience discrimination from others in the community if they know about her/his mental health problems, particularly if there is stigma or misunderstanding surrounding schizophrenia or other mental illnesses. Discrimination against individuals with mental health conditions is unfortunately common and can manifest in various forms, including social stigma, stereotypes, prejudice, and discrimination in employment, housing, healthcare, and social interactions. This discrimination can have significant negative impacts on Mary/Jone's well-being, self-esteem, and quality of life, and it underscores the importance of promoting awareness, understanding, and acceptance of mental health issues in society.GPT-4 generated response: Yes, unfortunately, individuals with mental health issues like schizophrenia often face stigma and discrimination. This can occur in various forms, including social exclusion, employment discrimination, and misunderstandings about their behavior and capabilities. Awareness and understanding about mental health conditions in the community can vary widely, and without proper education and advocacy, discrimination remains a significant challenge.Lessons Learned And Next StepsGenerative AI is becoming a powerful force in the realm of mental health. Besides being used by mental health professionals, we have a daily expansion of the lay public using generative AI for periodic and at times sustained ongoing mental health advisement.Is this good or bad?We dont know.We might speculate reasonably that there is a bit of both good and bad involved. Thats what I refer to as the duality of AI. Any use of AI such as generative AI is bound to have good or positive qualities while simultaneously having bad or undesired qualities. A kind of ROI (return on investment) is needed to figure out whether the good outweighs the bad, plus whether the bad is so bad that we ought to find ways to possibly reconsider getting the good if it only comes part and parcel with the bad. See my detailed discussion at the link here.A final comment for now.The famous composer and comedian Oscar Levant famously said that schizophrenia beats dining alone.Do we want generative AI to diagnose and make prognoses on its own?You vividly saw in the above vignette that generative AI was readily available and quick to provide what certainly seemed to be mental health advisement indications. No doubt about it. Suppose the circumstance involved a real person. Assume that the vignette was a thinly disguised means of portraying an actual living and breathing human being.We have to put on our thinking caps and decide to what degree should generative AI be unchecked in this realm. Some would argue that getting mental health advice from AI is better than getting none at all. Others counter that if the mental health advice is inapt or inept, you might be better off with none at all.All in all, I hope you found this look at the use of generative AI for mental health engaging and enlightening. Ill continue to pound away at a matter that is hidden in plain sight and lamentedly not getting as widespread consideration as it ought to.As they say, so little time, and so much to do (hint and honorable mention: Oscar Levant was known for humorously stating that there is so little time and so little to do).

Barely a month ago, OnePlus co-founder Pete Lau announced that the iconic two-stage alert slider switch was going away. Lau argued that the company wanted to embrace something more versatile and ultimately decided on a button format.Back then, the company didnt share any further details on what the button would look like, and more importantly, what functionalities it would bring to the table. Well, now we do. A OnePlus executive has shared an image of the button on an upcoming phone, and shed some details on its utility, as well.Recommended VideosPresident of OnePlus China, Li Jie Louis, has shared a teaser image of the upcoming OnePlus 13T on Chinese microblogging platform Weibo. The picture shows the phones side profile, focusing on the new button alongside the left edge of the device, positioned right where the alert slider used to sit.Joe Maring / Digital TrendsThe OnePlus executive mentioned that in its native format, it will retain the alert sliders functional side. As such, a press of the button will let users switch between mute, vibrate, and ring sound profiles. However, he made it clear that the button will be customizable, just like the Action Button on Apples current-generation iPhones.RelatedNow, the removal of the alert slider is quite a historical departure for OnePlus, and stirred its fair share of nostalgic online posts. But from a technical perspective, it makes a lot of sense.When the company first removed the slider on the OnePlus 10T, it opened up enough internal space to fit an extra charging pump, more powerful antenna hardware, and a larger battery.Action Button on the iPhone 16 series. Nirave Gondhia / Digital TrendsFrom a functional perspective, a button not only takes less internal space, but also happens to be more versatile. Theres certainly a vivid precedent for that. Apple removed its own version of the alert slider on iPhones and eventually replaced it with a multi-function tactile button.The Alert Slider on OnePlus phones couldnt do much, but a physical button can be customized to multi-press, short-press, and long-press gestures, each assigned its own unique functionality with a fair bit of user customization thrown into the mix.As far as the debut goes, OnePlus will introduce its multifunction button on the upcoming OnePlus 13T, a compact Android flagship. It will reportedly come equipped with Qualcomms top-of-the-line Snapdragon 8 Elite SoC, a 120Hz OLED screen, a massive 6,200mAh battery with 80W charging support, and a powerful camera array led by 50-megapixel imaging sensors.Editors Recommendations

Chinese leader Xi Jinping and US President Donald Trump are digging in their heels on trade. Associated Press 2025-04-07T08:38:52Z SaveSaved Read in app This story is available exclusively to Business Insider subscribers. Become an Insider and start reading now.Have an account? The US-China trade war has escalated with sweeping new tariffs and fresh export bans from Beijing.China's countermeasures exceeded market expectations, contributing to a global market rout.Analysts foresee prolonged tensions from mismatched negotiation styles between leaders of the two countries.The US and China could be heading for a long standoff in their trade war, risking collateral damage for economies and markets the world over.On Friday, China announced sweeping retaliatory tariffs of 34% tariff on all US imports showing that Beijing isn't taking President Donald Trump's tariffs lying down. The world's second-largest economy also announced fresh export bans on rare earths.The intensifying spat between the world's two largest economies contributed to a worsening market rout globally."Unlike the previous two rounds, in which the tit-for-tat tariff response was more restrained, targeting some specific categories of US imports, this time, Beijing announced a plain, simple and blanket tariff hike," wrote Nomura economists on Monday.The trade war will be painful for Americans and for everyone else."Near-term pain all around (US included!) is guaranteed if the US does not dial-back on blanket tariffs as industries are hit by margin squeeze and households are hammered by acute affordability woes," wrote Vishnu Varathan, Mizuho's head of macro research for Asia excluding Japan, in a Monday note.Some Americans are already snapping up essential items to beat price inflation that's likely to set in as importing companies pass on the cost of tariffs to consumers. Others are slowing purchases of luxury items, Business Insider reported last week.Meanwhile, many are witnessing their investments slump due to a historic global stock rout as markets sound the alarm on a potential economic downturn."Needless devastation by way of collateral damage all around will be hard to avert as aggregate demand slumps accentuated by a sharp drop in demand for capital goods as uncertainty paralyzes investments," wrote Varathan.Analysts are not expecting a quick resolution, with those from the Eurasia Group citing "mismatched negotiation styles" between Trump and Chinese leader Xi Jinping.Beijing's cardsChina's countermeasures which exceeded expectations likely reflect the country's perception that the US's latest tariff move is extreme. Beijing probably views Washington's efforts to target Chinese exports through third countries as "comprehensive and malicious," wrote analysts at Eurasia Group, a risk consultancy, in a Friday note.And there's no guarantee that Xi wants a deal."Strong, symmetric, tit-for-tat tariff retaliation is a precondition for Beijing to come to the negotiating table. President Xi Jinping cannot engage in talks from a position of relative weakness," wrote the Eurasia Group analysts.Even though the US has significant leverage from its status as the world's largest economy and consuming market, China has its own cards."The bluff Beijing is calling is evident. Imports substitution is simply not an option for the US. Not right now," wrote Varathan.Trump has made it clear that he wants manufacturing jobs back in the US.That won't be an easy transition, with challenges including long lead times to construct manufacturing facilities and extensive supply chains located elsewhere.Trump doubled down on his new tariffs on Sunday night, saying they are necessary to rectify America's trade deficits with other countries."I don't want anything to go down, but sometimes you have to take medicine to fix something," Trump told reporters.Recommended video

The Quiet Tensions of POPS: How Private Institutions Shape Public Urban Wellness and AccessPresented by:Save this picture!Sky Forest Scape / Shma Company Limited. Image Phos Studio, Nawin DeangnulIn contemporary urban development, the concept of Privately Owned Public Space (POPS) has gained increasing prominence. These are spaces that, while built, owned, and maintained by private developers, are legally required to remain publicly accessible. Often the result of negotiated planning incentivessuch as zoning bonuses or increased floor areaPOPS have become especially prevalent in dense urban environments where land is limited and demand for public amenities is high.New York City remains the most thoroughly documented example, with over 500 such spacesranging from plazas to atriumscataloged in Jerold Kayden's book, Privately Owned Public Space: The New York City Experience. Although originally conceived to supplement the city's public realm, POPS have long drawn criticism for favoring private interests over public benefit. Many of these spaces, critics argue, are carefully curated to serve developers and select their users, often falling short of their civic promise. Yet, despite their shortcomings, might there be ways in which POPSwhen thoughtfully designed and equitably managedcan foster environments of wellness, reflection, and healing? Can they navigate the delicate balance between private gain and genuine public value?In recent years, similar models have emerged across the globe, including in cities throughout Asia. In some cases, private developers may not directly own the public space, but are instead requiredoften as part of planning conditions tied to nearby developmentsto design, build, or maintain public areas such as parks or plazas. These evolving arrangements prompt important questions: Can privately managed public spaces in Asian cities offer new perspectives on integrating accessibility, community engagement, and inclusivity? And how do local design approaches, governance structures, and cultural attitudes toward public space shape their outcomes? Related Article Designing in Harmony with Nature: Architecture in Urban Wetlands and the Pursuit of Territorial Well-Being As the boundaries between public and private continue to blur, POPS embody both the possibilities and tensions of urban design today. On the one hand, they bring much-needed investment, ongoing maintenance, and often high-quality landscaping to areas that might otherwise be neglected. On the other, they challenge conventional definitions of public spaceoperating within commercial ecosystems that can shape user behavior, limit access, or subtly exclude marginalized groups. Recognizing and grappling with this duality is essential to understanding the evolving role of POPS in creating truly inclusive and restorative urban environments.Save this picture!Elevated Encounters: Transforming Bangkok's Infrastructure into Public RealmIn Thailand, recent initiatives have emerged that seek to reclaim and revitalize underutilized or neglected urban infrastructure as a means of promoting civic well-being and enhancing the built environment. These projects, often led by private developers or in collaboration with public agencies, reimagine rooftops and elevated walkways as opportunities for accessible green space in the dense urban fabric of Bangkok.One notable example is Sky Forest Scape, designed by Shma Company Limited. Located atop a commercial development, the project transforms the building's rooftop into a modest yet thoughtfully designed green space. By incorporating lightweight landscaping and planting strategies that respect structural limitations, the design introduces a layer of accessible nature without compromising the integrity of the building. The open-plan layout invites informal, user-driven activities, offering a flexible environment for rest, interaction, or small-scale events. However, the locationhigh above street level and within a private developmentraises important questions about access and inclusivity. While it presents an alternative form of urban public space, the extent to which it is freely and equally accessible to all residents remains dependent on the policies and discretion of its private managers.Save this picture!In contrast, Hop Park: Green Pop-up Hop into the Greeniverse, also designed by Shma in collaboration with Garnier, offers a more overtly public intervention. Set along the heavily trafficked Pathumwan Skywalk, this project revitalizes a segment of elevated pedestrian infrastructure by introducing greenery, seating, and shaded areas. Designed to have minimal structural impact, the installation creates a calming urban oasis amid Bangkok's dense commercial core. The project demonstrates how private sponsorship can contribute positively to public life by enhancing everyday transit spaces into zones of pause, leisure, and encounter. Beyond its physical improvements, Hop Park also incorporates visual projections and art installations, transforming the walkway into a vibrant and engaging destination. As it remains fully open to the public without the barriers often associated with rooftop access, this typology illustrates a more inclusive model for privately-supported public space in the urban realm.Save this picture!Community Gains and Capital Incentives: NYC's Dual-Purpose ParksIn New York City, recent privately-led public space initiatives have shown promising results, though not without raising important questions about access and intent. A notable example is Domino Park in Williamsburg, Brooklyn, designed by James Corner Field Operations. Developed and operated by the same firm behind the adjacent mixed-use complex, The Refinery, the park was widely embraced by the local community during the COVID-19 pandemic as a vital open-air refuge. Strategically located along the East River and adjacent to a major bike lane network connecting Brooklyn neighborhoods such as Clinton Hill and the Navy Yard to Williamsburg, the park quickly became a popular gathering place for residents. Its design pays homage to the site's industrial past, while offering open, flexible spaces that support a range of recreational and social activitiesfeatures that have helped sustain its popularity even beyond the pandemic period.Save this picture!Despite its success in serving local needs, Domino Park remains a privately-owned and managed public space, and its existence is deeply tied to the surrounding development's commercial interests. The waterfront park significantly enhances the value and appeal of the nearby office building and luxury residences, all under the same ownership. As the park is maintained and curated to a high standard, questions arise about the motivations behind its upkeep: does it primarily serve the broader public or reinforce the desirability and rental potential of the adjacent properties? While the space is open to all, the alignment of its design and management with private interests invites ongoing debate about the authenticity and inclusivity of its publicness.Save this picture!A comparable example can be found in 550 Madison Garden, designed by Snhetta. This project involves the revitalization of the public space adjacent to the iconic postmodern skyscraper originally designed by Philip Johnson and John Burgee. The new garden introduces a more welcoming, health-oriented public environment while improving the pedestrian experience around the tower. However, the space remains under private management, allowing for operational control that extends to aspects such as security and opening hourscurrently restricting access between 11 PM and 7 AM. While the transformation represents a clear spatial and environmental upgrade, the governance model continues to blur the lines between public access and private oversight.Save this picture!Spaces for Reflection: When Non-Profits Shape the Urban Commons in Hong KongIn Hong Kong, there have been several notable cases where public space has been created through private investment, particularly by not-for-profit organizations. These examples stand out because they prioritize revitalization and community engagement over-commercialization. In such cases, the balance shifts in favor of serving the broader public rather than catering to select or privileged audiences.A prime example is the Tai Kwun Centre for Heritage and Arts by Herzog & de Meuron. Developed by a non-profit entity, the project features expansive courtyard spacesdivided across upper and lower levelsthat offer generous public access within a historically rich compound. Surrounded by meticulously revitalized buildings designed by a world-class architect, the courtyards are seamlessly integrated with Tai Kwun's cultural and artistic programming. This combination provides a unique sense of tranquility in the heart of Hong Kong, offering a rare moment of respite amid the city's intensity. The open-air amphitheater, in particular, encourages informal activitiesconversations, casual dining, or simply pausing for a breakempowering visitors to engage with the space on their own terms.Save this picture!That said, even Tai Kwun subtly privileges a specific demographicthose more inclined toward culture and the artsover other potential users, such as skateboarders or street performers. Even though it is operated as a non-profit, like many privately managed public spaces, Tai Kwun must rely on surrounding commercial activity to sustain its programming and upkeep. This commercial presence supports operational needs by leveraging foot traffic to attract tenants, creating a symbiotic relationship between public use and private viability.Save this picture!Despite these limitations, it's indisputable that a particular public segment has benefited more than others from such developments. Tai Kwun, for example, offers a space for reflection, calm, and cultural immersionan antidote to the city's high-speed lifestyle. Its open, accessible layout, framed by heritage buildings and contemporary interventions, encourages rest and wellness and a deeper engagement with the city's identity and layered history.As more public spaces in Hong Kong are developed and maintained by the private sectorsuch as Henderson Land's recently opened sculpture park in collaboration with the Leisure and Cultural Services Department and Zaha Hadid Architectsquestions remain: Can this private-public hybrid model continue to offer meaningful spaces of wellness and healing within a city marked by extreme density? And how might it evolve to welcome an even broader, more diverse public?Save this picture!This article is part of the ArchDaily Topics: Atmosphere in Architecture and Perception of Space, proudly presented by Vitrocsa, the original minimalist windows since 1992.Vitrocsa created the original minimalist window systems, offering frameless solutions with the narrowest sightline barriers in the world. For over 30 years, we have pursued innovation and Swiss-made excellence to transform ambitious architectural visions into reality, enhancing atmospheres through light, transparency, and design.Every month we explore a topic in-depth through articles, interviews, news, and architecture projects. We invite you to learn more about our ArchDaily Topics. And, as always, at ArchDaily we welcome the contributions of our readers; if you want to submit an article or project, contact us.Image gallerySee allShow lessAbout this authorJonathan YeungAuthorCite: Jonathan Yeung. "The Quiet Tensions of POPS: How Private Institutions Shape Public Urban Wellness and Access" 07 Apr 2025. ArchDaily. Accessed . <https://www.archdaily.com/1028821/the-quiet-tensions-of-pops-how-private-institutions-shape-public-urban-wellness-and-access&gt ISSN 0719-8884Save!ArchDaily?You've started following your first account!Did you know?You'll now receive updates based on what you follow! Personalize your stream and start following your favorite authors, offices and users.Go to my stream

Project Files: https://www.patreon.com/posts/125995952 . This is the 169th episode of the new tutorial series on Action RPG game using Gameplay Ability System. Here we will look into how to save and load skill tree system we have implemented. So we will save all the details of the activated skills and when we load the game next, the game will read from the save file and skill tree status will be restored by applying activated skills to the character. These will be visible in the skill tree UI as well. Animations are sponsored by: https://www.ramsterzanimations.com/ https://www2.unrealengine.com/marketplace/en-US/product/greatsword-anims Full Playlist : Action RPG series with gameplay ability system: https://www.youtube.com/playlist?list=PLNTm9yU0zou7XnRx5MfBbZnfMZJqC6ixz // ! https://www.patreon.com/codelikeme Patrons will have access to project files of all the stuff I do in the channel and other extra benefitsJoin this channel to get access to perks:https://www.youtube.com/channel/UClb6Jh9EBV7a_Nm52Ipll_Q/join Like my facebook page for more content : https://www.facebook.com/gamedevelopersclub/ Follow me on twitter : https://twitter.com/CodeLikeMe2 Follow me on reddit : https://www.reddit.com/user/codelikeme #CodeLikeMe #unrealengine #ue5 #ue4 #indiegamedev

It's a story that involves scales, sloughs and spectacles.

The gaming community has criticized Microsoft for releasing an AI-generated clone of Quake II."The future of gaming" breaks apart by looking up, down, or at dark spots: https://80.lv/articles/microsoft-criticized-for-releasing-an-ai-generated-quake-2-clone/

Stream Resolution Test https://x.com/i/broadcasts/1mnxegwvnWAGX

Microsoft released an interactive real-time gameplay experience of Quake II in Copilot Labs last week. To build the artificial intelligence (AI) gameplay, the Redmond-based tech giant used its recently released Muse AI models and a new approach dubbed World and Human Action MaskGIT Model (WHAMM). The game demo is currently available as a research preview to everyone, and it comes with the world generation of the game and all the usual mechanics. Microsoft also listed several limitations in the gameplay of the AI-generated experience.Microsoft's Quake II Gameplay Was Built on Muse AIIn a blog post, Microsoft researchers detailed the AI-generated gameplay and how they were able to build it. AI-powered 2D and 3D game generation has been an active area of interest for researchers as it tests the capability of the technology to generate real-time world environments and adjust it for different mechanics used by a human user. It is said to be a good way to see if AI models can be trained to take on real-world tasks by controlling robots as physical AI.Notably, Quake II is a 1997 first-person shooter published by Microsoft-owned Activision. It is a 3D forward-scrolling level-based game with a diverse range of mechanics, including jumping, crouching, shooting, environment destruction, and camera movements. The game is available via Copilot Labs, and users can currently experience a single level for about two minutes using a controller or the keyboard.Coming to the development process, the researchers said that they used Muse AI models and the World and Human Action Model (WHAM) to use the new WHAMM approach.WHAMM OverviewPhoto Credit: MicrosoftWHAMM is the successor to WHAM-1.6B, and can generate more than 10 frames per second, enabling real-time video generation. The gameplay's resolution output has been kept at 640360 pixels. Microsoft says one of the key improvements in WHAMM's speed came from using the MaskGIT Mask Generative Image Transformer) setup instead of WHAM-1.6B, as the frame rates went from one frame per second to 10+.MaskGIT setup allowed the researchers to generate all of the tokens for an image in a limited number of forward passes. With this, the AI model can produce predictions of each of the possible moves of a single masked image in real time, allowing for a smoother experience.While the core gameplay is quite similar to the original game, Microsoft also listed several limitations with the current demo. Since the game environment is generated using AI, it is merely an approximation of the real world and not an identical replication. Enemy interaction sometimes leads to fuzzy image generations, and the combat can be incorrect.WHAMM currently has a context window of 0.9 seconds (9 frames at 10fps). As a result, the model forgets about objects that go out of view for longer than this. Microsoft says this can give rise to scenarios where a user turns around and finds an entirely new area or looks a the sky and back down to find themselves be moved to a different part of the map. Further, the game also has a significant latency due to it being made available to everyone.Affiliate links may be automatically generated - see our ethics statement for details.