Category Archives: values

Talking with chatGPT. A Philosophical Encounter …


eJournal: uffmm.org
ISSN 2567-6458, 14.January 2023 – 15.January 2023
Email: info@uffmm.org
Author: Gerd Doeben-Henisch
Email: gerd@doeben-henisch.de

CONTEXT

This is a special thought experiment as part of the uffmm.org blog.

INTRODUCTION

Since its recent ‘coming out’ (November 2022) the chatbot chatGPT from openai.com has gained a growing public attention: Posts in blogs, Journals, newspapers, TV … Even I noticed this new presence.

The one way to understand it is ‘looking behind the scene’, looking ‘into the system’, which is in principle possible. But because the direct inspection of the human brain would you tell nearly nothing about its fantastic properties (even not in the light of the interpretation of the brain sciences) and as well, looking into the ‘chips of computer hardware’ would you tell too nearly nothing about what a computer-system is able to do, so it will in a first step be of no great help, to fill many pages with the algorithms of chatGPT. As such an isolated algorithms doesn’t tell too much, and a whole network of such algorithms doesn’t either.

What perhaps can be interesting is a ‘comparison’ between our human behavior (and understanding) with the behavior of chatGPT and some ‘implicit meaning’ embedded in this behavior.

Thus curious about what this chatGBT is I logged into the system and started interacting with the chatGBT software in the offered ‘playground’. The first two chats have been a little bit like ‘swaying back and forth’, my next two chats have become quite interesting.

After this experience I decided to document these chats in this blog in a 1-to-1 fashion thus enabling further reflections about them later. [3] Rather quickly one can learn that this adventure has many different dimensions from ‘simply being impressed’ until ‘deep philosophical thinking’.

OK, let’s start with doing it.

The 8000-signs embracing chat No.4 ends up with the following paragraph:

Human: OK, this all sums up to the conclusion that human rationality is composed of emotions, spiritual experience as well as conscious as well as unconscious cognitive processes. Do I miss something important?

Machine (citing human documents): No, you have accurately summed up the components of human rationality. Additionally, human rationality is also composed of social and cultural influences, which can shape and inform our understanding of the world and our decisions. Additionally, human rationality is often impacted by our values and beliefs, which can provide a moral foundation for our behavior and decision making. Finally, human rationality is also impacted by our environment, which can provide a source of information and insight.

For more coments see:

COMMENT

wkp := wikipedia

[1] wkp en: chatGPT, URL: https://en.wikipedia.org/wiki/ChatGPT, is a chatbot with the technology of a ‘Generative Pre-trained Transformer’. See more there.

[2] wkp en: chatbot, URL: https://en.wikipedia.org/wiki/Chatbot, is a software which is able to interact in the format of a dialogue (which tells nothing and all …)

[3] During the first two chats I didn’t save the dialogues. This I started beginning with chat No.3