Session 5 with ChatGPT 5.2
Reading Bernie Goldbach’s blog entry, Using Copilot on My Mobile Phone, I thought I’d give his three tests a try on ChatGPT 5.2. I didn’t quite do them since I used Project Iceberg PDF for both the “break down” and “creating an audio clip.” Also, I relied on browser-version of ChatGPT.
The tests include:
- We will break down a PDF from PWC.
- And we will see if Copilot can make a pie chart from a screenshot of a survey.
- During a text-to-speech breakout, we will create an audio clip from MIT Project Iceberg
Pie Chart
For fun, I started with the pie chart test. I started with this image:
And asked ChatGPT to make a pie chart:
make a pie chart/graph from the attached image
Not a very sophisticated prompt, I know. Here’s the result, nonetheless:
Summarizing a PDF
I asked ChatGPT to give me a prompt for summarizing a PDF, because, why not? This is what it offered:
Task
Analyze the attached PDF and produce a clear, accurate summary for practical use.Instructions
- First, identify the document’s purpose, audience, and main claim (1–2 sentences).
- Provide a concise executive summary (5–7 bullet points) capturing only what the document explicitly states.
- Extract key ideas or findings, organized by section or theme.
- List important data, examples, definitions, or recommendations exactly as presented.
- Flag any unclear, ambiguous, or potentially misleading claims.
- Note what is not included but a reader might reasonably expect.
- End with a short “Use This If…” section explaining when this PDF would be most helpful.
Accuracy Rules
- Do not infer beyond the text.
- Do not invent sources, data, or conclusions.
- If information is missing or unclear, say so explicitly.
Output Format
- Headings and bullet points only
- Plain language
- No filler, no speculation
The result was quite difficult to process, so I asked it to simplify using the VIVA framework for a 15 year old:
VIVA — Explained Simply
Verify — What is the big idea?
- AI is changing many jobs, not just tech jobs.
- We usually notice AI in coding or computers, but most of its impact is hidden.
- The Iceberg Index is a way to measure how much of a job AI could help with.
- Most AI impact is below the surface, like the hidden part of an iceberg.
Illustrate — What does that look like?
- What we see: AI helping programmers write code.
- What we don’t see: AI helping with paperwork, schedules, emails, and reports in offices, hospitals, schools, and factories.
- Example: A nurse uses AI to handle forms, so they can spend more time helping patients.
- Iceberg idea: The small part above water is tech jobs. The big part under water is everyday work.
Validate — How do we know this is real?
- Researchers compared job skills and found their model matches real career changes most of the time.
- They checked where people actually use AI and saw similar patterns.
- The study is careful: it does not say people will lose jobs—only that jobs will change.
Apply — Why should this matter to you?
- Jobs in the future will still need people, but with different skills.
- Learning how to think, organize, explain, and solve problems will matter more.
- Schools and leaders can prepare people before jobs change, instead of reacting too late.
- Understanding AI early helps you be ready, not surprised.
One-sentence takeaway:
AI isn’t just changing tech jobs—it’s quietly changing how almost everyone works, and the Iceberg Index helps us see it coming.
Audio File Generation
ChatGPT actually generated an audio file…so cool.