SITIC Topic Forum, Montag, 18. März 2024, 11:30 – 18:00 Uhr

KI-Anwendungen

Hintergrund

Künstliche Intelligenz (KI) eröffnet mit atemberaubender Geschwindigkeit völlig neue Anwendungen von Informationstechnologien (IT).
Jules Verne’s Überzeugung vor über hundert Jahren, dass alles was sich Menschen heute vorstellen können, andere Menschen morgen realisieren werden, wird immer be|greifbarer.

Gehört «Never Say Never» fortan zu einem innovativen Mindset?

Das Risiko, vom technologischen Fortschritt abgehängt zu werden, scheint nie grösser gewesen zu sein.
Jede Organisation ist herausgefordert, sich mit der raschen KI-Entwicklung auseinanderzusetzen, mit Pilotprojekten zeitnah KI-Kompetenz aufzubauen, KI-Einsatzpotentiale zu antizipieren, Business Cases zu evaluieren und KI-Anwendungen zu realisieren.

«Never Say Never»
Photo 278671301 © Olena Rudo | Dreamstime.com

Welche Anwendungsmöglichkeiten für KI gibt es in jenen Bereichen, in denen die menschliche Interaktion bislang ein wesentlicher Teil der Leistungserbringung war?
Diese Frage wird in diesem Topic Forum an zwei Fallbeispielen diskutiert:

  • Beantwortung von Fragen von Kund*innen, respektive Klient*innen,
  • Erstellung und Vermittlung von fachlichen Inhalten für die Ausbildung.

Der Kanton Zürich stellt zwei seiner KI-Projekte vor, die Entwicklung eines Chatbots und die Erstellung von Virtual Reality Inhalten für die Ausbildung.
Die bisherigen Erfolge werden in Demos gezeigt, aber auch die besonderen Schwierigkeit und die aktuellen Herausforderungen werden besprochen.

Die Teilnehmenden können sich aktiv in die Diskussionen einbringen, um anhand einiger Leitfragen Impulse zu vermitteln und zu erhalten.

Leitfragen

Topic Forum und Workshop sind durch die folgenden fünf Leitfragen motiviert:

Allgemein:

  • Was unterscheidet die Entwicklung von KI-Anwendungen von der Entwicklung von der Entwicklung von Software und «normalen» digitalen Diensten?
  • Wie kann die Qualität von KI-generierten Anwendungen und Inhalten geprüft und sichergestellt werden?
  • Welche rechtlichen und ethischen Aspekte müssen bei der Nutzung von KI für die Interaktion mit Menschen berücksichtigt werden?

Speziell:

  • Was sind die kritischen Erfolgsfaktoren beim Interaktionsdesign von KI-basierten Chatbots?
  • Was sind die kritischen Erfolgsfaktoren bei der Nutzung von KI für die Erstellung von Virtual Reality Inhalten?

Gastgeber

Kanton Zürich
Amt für Informatik
Waltersbachstrasse 5
8090 Zürich

Veranstaltungsort

Polizei- und Justizzentrum Zürich
Güterstrasse 33
8004 Zürich

Die Lokation erfordert eine strikte Zutrittskontrolle.
Rechtzeitige Ankunft erwünscht.

Als Teilnehmende/r erhalten Sie eine persönliche Einladung via E-Mail.
Diese Einladung ist Ihr Zutrittsticket für den Ein und Austritt und ist zwingend mitzuführen, ausgedruckt oder elektronisch.
Bitte nehmen Sie deshalb ein amtliches Bilddokument mit (Pass, ID, Führerausweis der Schweiz, Aufenthaltsbewilligung oder Niederlassungsbewilligung).
Die Sicherheitskontrolle entspricht jener des Flughafens.
Somit nur das Wichtigste mitnehmen, alles Andere muss abgegeben werden (e.g. Sackmesser).

Teilnehmende

Willkommen sind Business IT Professionals, welche im Unternehmen Aufgaben als

  • IT-Führungskraft,
  • digitaler Unternehmensentwickler,
  • Unternehmensarchitekt

wahrnehmen.

Moderation

Reinhard Riedl (SITIC Vorstandsmitglied)

Agenda

11:30 – 11:50
Eintreffen und Zutrittskontrolle inkl. Begleitservice zum Veranstaltungsraum.
Anschliessend Transfer ins EG für das gemeinsame Mittagessen.
KAPO, Stefan Epp & Jimmy (Rudolf) Ehrbar

11:50 – 12:50
Mittagessen und Networking im Restaurant EG.
Die Teilnehmer müssen das Essen bei Kasse 3 melden.

12:50 – 13:00
Dislozieren zu den Veranstaltungsräumen
Stefan Epp & Jimmy (Rudolf) Ehrbar

13:00 – 13:10
Eröffnung & Einführung
Reinhard Riedl, SITIC, und Marc Bühler, Kanton Zürich

13:10 – 13:40
Generative AI – Dystopie, Begleiter oder Tool?
Jan Simon, aity|BEKB

«Welcome to the age of AI natives” – Der Einfluss von Generative AI auf unsere Zeit wird von einigen mit dem Einfluss der beginnenden Nutzung der Elektrizität Mitte des 19. Jahrhunderts verglichen. Der Beitrag stellt eine Übersicht der derzeitigen Diskussionen und Einsatzgebiete dar, mit einem Fokus auf den Einsatz rund um die Software-Entwicklung. Er soll dazu beitragen, eine offene Diskussion über die Risiken- und Nutzenaspekte zu ermöglichen.

13:40 – 13:55
Diskussion

13:55 – 14:25
Large Language Models in der öffentlichen Verwaltung
Václav Pechtor, Kanton Zürich

Dieser Vortrag beleuchtet die Funktionsweise und Grenzen von großen Sprachmodellen (LLMs) im öffentlichen Sektor. Wir präsentieren Erkenntnisse aus aktueller Forschung und diskutieren potentielle Anwendungen, Herausforderungen und Empfehlungen für den Einsatz.

14:25 – 14:40
Diskussion

14:40 – 14:45
Kurzpause

14:45 – 15:15
Erste Erfahrungen und Erkenntnisse beim Start der KI in der Verwaltung
Cyrill Hagmann & Marc Zeugin

  • Update Gesamtvorhaben Bot Strassenverkehrsamt​
  • Vorstellung neuer Funktionen​
  • Lösungs-Demo​
  • Ausblick auf kommende Entwicklungen​
  • Erste Erfahrungen

15:15 – 15:30
Diskussion

15:30 – 15:50
Pause

15:50 – 16:20
CC XR –  Ein organisationsübergreifendes Innovations- und Dienstleistungsprojekt
Kantonspolizei Zürich

Innovationsthemen wie «Virtual Reality» und künstliche Intelligenz erfordern eine effiziente organisationsübergreifende Zusammenarbeit, ein breites Wissen und eine leistungsfähige IT-Infrastruktur. Um die Themenführerschaft zu erreichen ist es notwendig, dass öffentliche Organisationen mit ihren beschränkten Ressourcen synergistisch zusammenarbeiten.

16:20 – 16:40
Einsatz der 3D-Anwendung in der Ausbildung
Kantonspolizei Zürich

Das Competence Center XR (CC XR), ist eine prototypisches Beispiel eines partnerschaftlichen Konstrukts zwischen der Kantonspolizei Zürich, der Stadtpolizei Zürich, dem Forensischen Institut und der Zürcher Polizeischule zur Entwicklung von zukunftsgerichteten XR-Applikationen für verschiedene polizeiliche und forensische Fragestellungen und Anwendungsfelder. Die Schaffung der technischen, organisatorischen und rechtlichen Grundlagen und der produktive Einsatz von AI-Technologien ist dabei in verschiedenen Anwendungsszenarien ein gewichtiger Erfolgsfaktor.

16:40 – 17:10
Gruppenarbeiten
Weitere Entwicklung und Ideen mit KI-Möglichkeiten auch in Ausbildungssequenzen.

17:10 – 17:20
Abschluss

17:20 – 18:00
Apéro für Austausch und Networking.

Anmeldung

Verbindliche Anmeldung bitte via Email an kurt.wehrli@sitic.org

Anmeldetermin Donnerstag, 7. März 2024, 18 Uhr.

Danach können keine Anmeldungen mehr angenommen werden.

Kosten

Für SITIC-Mitglieder ist die Teilnahme im Rahmen der Jahresmitgliedschaft unentgeltlich.
Nicht-Mitgliedern werden 375 CHF in Rechnung gestellt.

Three AI-Questions For ChatGPT

1. «What is artificial intelligence?»

2. «What are the opportunities and benefits of artificial intelligence?»

3. «What are the risks and disadvantages of artificial intelligence?»

Unabridged answers of ChatGPT on February 18, 2024:

1. «What is artificial intelligence?»

Artificial Intelligence (AI) refers to the simulation of human intelligence in machines that are programmed to think and learn like humans. The goal of AI is to create systems that can perform tasks that typically require human intelligence, such as visual perception, speech recognition, decision-making, and language translation.

There are two main types of AI:

  1. Narrow AI (or Weak AI): This type of AI is designed to perform a specific task or a narrow set of tasks. Examples include speech recognition, image recognition, and language translation. Narrow AI is the most common form of AI that we encounter in our daily lives.
  2. General AI (or Strong AI): This refers to a level of artificial intelligence that can understand, learn, and apply knowledge across a wide range of tasks at a level comparable to human intelligence. General AI is still largely theoretical and has not been achieved as of my last knowledge update in January 2022.

AI techniques include machine learning, where algorithms are trained on large datasets to improve their performance over time, and deep learning, which involves neural networks with many layers (deep neural networks) to enable complex pattern recognition and decision-making.

AI applications are diverse and can be found in areas such as healthcare, finance, transportation, education, and more. As AI continues to advance, ethical considerations and responsible AI development are becoming increasingly important topics of discussion.

2. «What are the opportunities and benefits of artificial intelligence?»

Artificial Intelligence (AI) presents a wide range of opportunities and benefits across various industries. Some key advantages include:

  1. Efficiency and Automation: AI can automate repetitive tasks, freeing up human workers to focus on more complex and creative aspects of their jobs. This can lead to increased productivity and efficiency.
  2. Data Analysis and Insights: AI excels at processing and analyzing vast amounts of data quickly and accurately. This ability allows businesses to derive valuable insights from their data, helping in better decision-making.
  3. Personalization: AI-powered systems can analyze user behavior and preferences to provide personalized recommendations, whether in e-commerce, content delivery, or personalized learning experiences.
  4. Cost Reduction: Automation through AI can lead to cost savings in various industries by reducing the need for manual labor and streamlining processes.
  5. Improved Healthcare: AI is being used in medical research, diagnostics, and personalized medicine. It can help in analyzing medical images, predicting patient outcomes, and developing treatment plans.
  6. Enhanced Customer Experience: AI-powered chatbots, virtual assistants, and customer service systems can provide quick and personalized responses, improving overall customer satisfaction.
  7. Innovations in Business Models: AI opens the door to new business models and revenue streams. Companies can develop innovative products and services that leverage AI capabilities.
  8. Cybersecurity: AI can be employed to enhance cybersecurity measures by detecting and responding to threats in real-time, identifying patterns of malicious behavior, and improving overall system security.
  9. Education and Training: AI can revolutionize education by providing personalized learning experiences, automating administrative tasks, and assisting teachers in delivering more effective lessons.
  10. Space Exploration: AI is being used in space exploration for tasks such as autonomous navigation, data analysis, and mission planning.

Despite these opportunities, it’s crucial to consider ethical considerations, privacy concerns, and potential job displacement. Striking a balance and ensuring responsible AI development and deployment is essential to maximize the benefits while mitigating potential risks.

3. «What are the risks and disadvantages of artificial intelligence?»

While artificial intelligence (AI) offers numerous benefits, it also poses certain risks and disadvantages that need to be carefully considered. Some of the key concerns include:

  1. Job Displacement: Automation and AI technologies can lead to job displacement as certain tasks and roles become automated. This can result in unemployment or the need for workers to acquire new skills to adapt to changing job requirements.
  2. Bias and Fairness: AI systems can inherit biases present in the data used for training. If the training data is biased, the AI system may perpetuate and even exacerbate existing biases, leading to unfair or discriminatory outcomes.
  3. Privacy Concerns: AI often involves the processing and analysis of large amounts of personal data. The use of AI in surveillance, facial recognition, and data mining raises privacy concerns and can infringe on individuals’ rights if not properly regulated and monitored.
  4. Ethical Concerns: The development of AI raises ethical questions, such as the potential misuse of AI for malicious purposes, the impact on personal autonomy, and the accountability for AI decisions, especially in critical areas like healthcare, finance, and criminal justice.
  5. Security Risks: AI systems can be vulnerable to adversarial attacks, where individuals intentionally manipulate input data to deceive the AI system. Additionally, the interconnected nature of AI systems can expose them to cybersecurity threats.
  6. Lack of Transparency: Deep learning algorithms, in particular, can be complex and difficult to interpret. The lack of transparency in some AI models can make it challenging to understand how decisions are made, leading to a lack of trust in the technology.
  7. Overreliance on AI: Overreliance on AI systems without human oversight can lead to errors and unintended consequences. It’s essential to maintain a balance between automation and human intervention, especially in critical decision-making processes.
  8. High Costs: Implementing AI systems, especially advanced ones, can involve significant upfront costs for development, training, and maintenance. This may pose a barrier to smaller businesses or organizations with limited resources.
  9. Job Shifts and Skill Gaps: While AI may eliminate some jobs, it also creates a demand for new skills. There may be a gap between the skills required for emerging AI-related roles and the existing workforce’s skill set, leading to potential challenges in workforce transition.

Addressing these risks requires a multidisciplinary approach involving ethical AI development, transparent algorithms, robust cybersecurity measures, and thoughtful regulation and policy frameworks to ensure responsible and fair AI deployment.