Harvard University's ban on "feeding" ChatGPT and the meaning of China´s stellar Pisa results

https://19-pacheco-torgal-19.blogspot.com/2023/07/ranking-das-empresas-mais-obcecadas_11.html

In a previous post, link above, a reference was made to the recent case of a major US telecommunications company that imposed a ban on its employees from using ChaGPT. The purpose of this restriction was to safeguard the privacy of customer information, as the company recognized the potential risks associated with the "feed" of generative AI tools. Interestingly, Harvard University recently made public a set of guidelines (https://huit.harvard.edu/news/ai-guidelines) regarding the use of generative AI models. These guidelines explicitly prohibit feeding confidential data or non-public research data into those models.

With regard to ChatGPT, it is worth noting that yesterday, the esteemed journal Nature published a study demonstrating that ChatGPT does not offer significant advantages to individuals with strong writing skills. However, it does play a crucial role in reducing the existing inequality between those with weak writing skills and those with greater proficiency. This contributes not only to the democratization of writing ability but also to its devaluation.  https://www.nature.com/articles/d41586-023-02270-9

Asked which areas generative AI will not replace humans, ChatGPT provided the answer reproduced below in blue color. However, it is important to consider that nanotechnology is already operating at a scale much smaller than the "fine motor skills" mentioned in paragraph 4. For instance, chips with dimensions in the range of a few nanometers, thousands of times smaller than the thickness of a human hair, are already being produced. This indicates that the human advantage in the domain of "fine motor skills" may not be long-lasting and will eventually be surpassed by machines. Still, human creativity, emotions, and ethics will continue to be key differentiators. In light of this, it is worth revisiting the content of a 2019 post on the meaning of world leadership for Chinese students on the PISA test, and where it was written that the future of education will have to train innovative humans, with high ethical and moral standards. https://pacheco-torgal.blogspot.com/2019/12/pisa-best-students-in-world.html

"Although generative AI has made significant advances and has the ability to perform complex tasks, there are areas where humans still play essential roles and will not be easily replaced. Here are some of these areas:

1. Creativity and Art: While generative AI can generate creative content such as music, paintings, and texts, it often relies on existing patterns and data. Originality, emotional expression, and the ability to transcend conventions are aspects where humans still have an advantage.

2. Empathy and Human Interaction: Generative AI can simulate conversations and human interactions to some extent, but genuine empathy and emotional understanding are still unique human skills. Human interactions require a deep understanding of emotions, social context, and nuances that AI is still far from matching.

3. Ethical Decision Making: Generative AI operates based on algorithms and data provided to it, but it lacks the ability to discern complex ethical values or consider the moral and philosophical aspects involved in important decisions. Ethical issues require human judgment, weighing of values, and contextual considerations.

4. Motor Skills and Physical Manipulation: While generative AI can generate images, videos, and motion simulations, it does not have the ability to manipulate physical objects in the real world with the same dexterity and precision as humans. Tasks that require fine motor skills, such as surgery or assembling complex components, are still dominated by humans.

5. Creating Deep Emotional Connections: Generative AI can offer assistance and interaction, but it cannot yet replicate the deep emotional connections that humans develop with each other. Personal relationships, genuine empathy, and emotional support are aspects of human interaction that cannot be completely replaced by AI.

Universidade de Harvard acaba de proibir a "alimentação" do ChatGPT

https://19-pacheco-torgal-19.blogspot.com/2023/07/ranking-das-empresas-mais-obcecadas_11.html

Num post anterior, acessível no link acima, foi feita referência ao facto de uma conhecida empresa de telecomunicações Norte-Americana ter proibido os seus funcionários de utilizar o ChaGPT, para  assim evitar que a "alimentação" dessa ferramenta de IA generativa, possa colocar em risco a privacidade das informações dos clientes. Curiosamente, ontem a universidade de Harvard tornou público um conjunto de  instruções, quanto à utilização de modelos de IA generativa https://huit.harvard.edu/news/ai-guidelines onde consta a proibição de inserção nos referidos modelos de dados confidenciais ou dados de pesquisas não públicas. 

Sobre o ChatGPT é igualmente interessante constatar que também ontem a conhecida revista Nature divulgou um estudo que mostra que o ChatGPT não fornece grandes vantagens aqueles que possuem elevadas capacidades de escrita, mas que irá reduzir grandemente a desigualdade existente entre esses e aqueles que possuem fracas capacidades de escrita, contribuindo não só para a democratização dessa capacidade mas também para a desvalorização da mesma https://www.nature.com/articles/d41586-023-02270-9

Perguntado sobre as áreas em que a IA generativa não irá substituir os humanos o ChatGPT devolve a resposta que abaixo se reproduz. Tendo porém em conta que a nanotecnologia já opera a uma escala muitíssimo inferior às capacidades da motricidade fina mencionadas na alínea 4 (já se produzem chips com poucos nanómetros, milhares de vezes mais pequenos do que a espessura de um cabelo) isso significa que essa vantagem humana, não terá uma vida longa, sobram assim na contabilização (no médio prazo) das vantagens humanas face à máquina, a criatividade, as emoções e a ética. Nesse contexto vale a pena revisitar o conteúdo de um post de 2019, sobre o significado da liderança mundial dos estudantes Chineses no teste PISA e onde se escreveu que o futuro da educação (para enfrentar os gravíssimos desafios com que se confronta a Humanidade) terá de passar por formar humanos inovadores, com elevados padrões éticos e morais.  https://pacheco-torgal.blogspot.com/2019/12/pisa-best-students-in-world.html

Embora a IA generativa tenha feito avanços significativos e possua a capacidade de realizar tarefas complexas, existem áreas em que os humanos ainda desempenham papéis essenciais e não serão facilmente substituídos. Aqui estão algumas dessas áreas:

1. Criatividade e Arte: Embora a IA generativa possa gerar conteúdo criativo, como música, pinturas e textos, ela geralmente se baseia em padrões e dados existentes. A originalidade, a expressão emocional e a capacidade de transcender as convenções são aspectos em que os humanos ainda têm uma vantagem.

2. Empatia e Interação Humana: A IA generativa pode simular conversas e interações humanas até certo ponto, mas a verdadeira empatia e compreensão emocional ainda são habilidades exclusivas dos seres humanos. As interações humanas requerem uma compreensão profunda das emoções, contexto social e nuances que a IA ainda está longe de igualar.

3. Tomada de Decisão Ética: A IA generativa opera com base em algoritmos e dados fornecidos a ela, mas não possui a capacidade de discernir valores éticos complexos ou de considerar os aspectos morais e filosóficos envolvidos em decisões importantes. Questões éticas exigem julgamento humano, ponderação de valores e considerações contextuais.

4. Habilidades Motoras e Manipulação Física: Embora a IA generativa possa gerar imagens, vídeos e simulações de movimento, ela não possui a capacidade de manipular objetos físicos no mundo real com a mesma destreza e precisão dos seres humanos. Tarefas que exigem habilidades motoras finas, como cirurgia ou montagem de componentes complexos, ainda são dominadas pelos humanos.

5. Criar Conexões Emocionais Profundas: A IA generativa pode oferecer assistência e interação, mas ainda não pode replicar as conexões emocionais profundas que os seres humanos desenvolvem entre si. Relacionamentos pessoais, empatia genuína e apoio emocional são aspectos da interação humana que não podem ser completamente substituídos pela IA.

https://chat.openai.com/share/f467ad8d-24e2-441d-afd5-86385a905c1d

The Economist - ChatGPT advice for solving a serious problem in the UK (and US)

In a recent article published in The Economist, link below, it was learned not only that taxpayers in the United Kingdom pay more than 4000 euros per month for each prisoner, but also that the criminal justice of that country is going through a very problematic phase because since the 90s, the country's prison population has grown by 200% to more than 80,000 inmates (142 per 100,000 people compared to the EU average of 109), although paradoxically the number of crimes has been constantly decreasing, now being 400% lower than the value recorded in the 90s. https://www.economist.com/britain/2023/06/26/why-short-prison-sentences-in-england-and-wales-are-a-disaster

Still, since the USA incarceration rate is 530 people for every 100,000 in its population (almost 400% higher than UK) it means that the UK jail problem is almost like Heaven on Earth, at least when compared to the unbelievable American nightmare https://scholarship.law.wm.edu/cgi/viewcontent.cgi?article=1606&context=popular_media

When asked to provide a solution to the aforementioned issue, ChatGPT advised the following:

"Reducing high incarceration rates is a complex issue that requires a comprehensive approach. Here are some advisable solutions that can help address this problem:

1. Sentencing Reform: Review and reform sentencing policies to ensure they are fair, proportionate, and focused on rehabilitation rather than just punishment. Implement alternatives to incarceration such as community service, probation, or restorative justice programs for non-violent offenders.

2. Focus on Rehabilitation: Shift the emphasis from punishment to rehabilitation within the criminal justice system. Provide access to education, vocational training, mental health services, and substance abuse treatment to address the underlying causes of criminal behavior and reduce recidivism rates.

3. Pretrial Reforms: Implement measures to reduce the use of pretrial detention. This can include using risk assessment tools to determine the likelihood of flight or danger to the community, promoting alternatives to cash bail, and ensuring access to legal representation for individuals awaiting trial.

4. Address Socioeconomic Factors: Address the root causes of crime by tackling socioeconomic disparities and promoting economic opportunities. Invest in education, job training, affordable housing, and community development initiatives, particularly in disadvantaged areas.

5. Diversion Programs: Expand the use of diversion programs that redirect individuals away from the criminal justice system, especially for non-violent offenses. These programs can involve counseling, treatment programs, or community-based interventions as alternatives to formal prosecution.

6. Drug Policy Reform: Reevaluate drug policies, particularly for non-violent drug offenses. Focus on treating drug addiction as a public health issue rather than a criminal one, with an emphasis on prevention, harm reduction strategies, and access to treatment.

7. Collaboration and Coordination: Foster collaboration between criminal justice agencies, social services, and community organizations to develop holistic approaches to crime prevention and rehabilitation. Encourage partnerships that promote information sharing, evidence-based practices, and support networks for individuals reentering society after incarceration.

8. Community Policing: Promote community-oriented policing models that prioritize building trust, positive relationships, and cooperation between law enforcement agencies and the communities they serve. This can help prevent crime, address underlying issues, and reduce the need for incarceration.

9. Address Racial Disparities: Address racial and ethnic disparities within the criminal justice system. Implement measures to reduce biases at all stages of the criminal justice process, including policing, arrests, charging, sentencing, and parole decisions.

10. Data-Driven Approach: Use data and research to inform policy decisions and evaluate the effectiveness of different interventions. Regularly assess the impact of reforms and make adjustments as necessary.

It is important to note that these solutions should be tailored to the specific context and needs of each jurisdiction. There is no one-size-fits-all approach, and a combination of strategies is often required to effectively reduce high incarceration rates while maintaining public safety."