J&P
Sverige / USA
J&P

ChatGPT SH! (Start Here)

A top-level, “Start Here”, page for all things ChatGPT.

WARNINGS

On using AI tools like ChatGPT

  1. NEVER enter any personal, personally identifiable information (PII) or business sensitive information!
  2. NEVER trust responses without both your own sanity checks and follow-up questions as applicable.
  3. Keep in mind ‘the devil is the the details’ and think …

DO CHECK out https://jandp.biz/ChatGTP – Introduction, WARNINGS section for more details.

Getting Started

Examples of Q&As

(Laws/Legal) One Area Where AI Can Be Really Helpful…

… as ASSISTANT, with guidance into law texts and cases, but AS assistant – “you” really still need to know what you are doing!

One infamous case of things going wrong [text from CIO .. Famous AI Disasters] (Google for more sources around this case – In June 2023 Judge Castel imposed):

ChatGPT hallucinates court cases

Advances made in 2023 by large language models (LLMs) have stoked widespread interest in the transformative potential of gen AI across nearly every industry and corner of the business. OpenAI’s ChatGPT has been at the center of this surge in interest but the technology still has a long way to go before it can reliably take over most processes, as attorney Steven Schwartz learned when he found himself in hot water with US District Judge Kevin Castel in 2023 after using ChatGPT to research precedents in a suit against Colombian airline Avianca.

In an affidavit, Schwartz told the court it was the first time he had used ChatGPT as a legal research source and was “unaware of the possibility that its content could be false.” He admitted he hadn’t confirmed the sources provided by the AI chatbot, and  regretted using gen AI to supplement his legal research, adding he’ll never do so in the future without verifying authenticity.

In June 2023, Judge Castel imposed a $5,000 fine on Schwartz and LoDuca, and in a separate ruling in June, Judge Castel dismissed Mata’s lawsuit against Avianca.

Summarize a longer text, like an article, report, …”

This is an example of very potentially powerful functionality.

To quickly get some form of summary of longer texts. (Example below is some 6 pages in print and one can very easily get like a one-paragraph summary using ChatGPT).

BUT, it can of course summarize is completely WRONG. This is a great example of dangers with AI – “‘100%’ on topic” or ” ‘100%’ OFF topic”

In this particular case, summary texts DO seem plausible, based on I/J actually reading text, plus own knowledge from reading other texts.

Article published 2024-10-21, read sometime around that timeframe, and summarized using ChatGPT around also same time.

My entry: Can you please summarize https://www.texasobserver.org/how-mass-deportations-would-devastate-texas/

ChatGPT said:

Searched 2 sites

The Texas Observer article highlights the economic and social impacts that large-scale deportations would have on Texas. Given Texas’s significant immigrant population, mass deportations could severely affect the state’s workforce, especially in essential industries like agriculture, construction, and service sectors. Such actions may also burden local economies, reduce tax revenues, and lead to shortages in key areas. Beyond economic impact, the article notes the potential harm to families and communities, emphasizing how deportations could increase poverty, destabilize families, and place additional strain on social services.

You said:

In a suitable number of bullets please

ChatGPT said:

  • Texas’s economy could suffer from labor shortages, particularly in agriculture, construction, and service sectors.
  • Deportations would reduce tax revenue and harm local businesses dependent on immigrant spending.
  • Families and communities may experience destabilization, increased poverty, and mental health impacts.
  • Social services may be strained by increased demand for family and child welfare support.

For more, you can view the full article here.