View ChatGPT and Claude Markdown output on Mac

ChatGPT and Claude write their answers in Markdown, so to read them with real headings, lists, tables, equations and code blocks, save the text as a .md file and open it in Unmarked on your Mac. The chat window renders the formatting live, but the moment you copy the text out, you get the raw source: hashes, asterisks, pipes and dollar signs. Unmarked renders that source the way it was meant to look.

This is also how you read the Markdown files assistants leave behind: a README.md, a CLAUDE.md, a plan or report an agent wrote into your project.

Why the copied answer looks like raw symbols

In the chat window, a heading shows as big bold text and a list shows as neat bullets. That rendering belongs to the website. Copy the answer into a plain note or a .txt file and the rendering is gone. What's left is the actual Markdown the model wrote:

## Setting up the project
 
Run these steps in order:
 
1. Install the dependencies
2. Copy the example config
3. Start the dev server
 
| Command | What it does |
| --- | --- |
| `npm run dev` | Starts the local server |
| `npm run build` | Builds for production |

That is correct Markdown. It's just unrendered. Open it in something that reads Markdown and the ## becomes a heading, the numbers become an ordered list, and the pipe table becomes a real table with cell borders.

Save the answer as a .md file

The trick is to keep the text as plain Markdown and give the file a .md extension.

1. In ChatGPT or Claude, copy the full answer. Many answers have a copy button at the corner of the message; use it so you get the source, not a styled paste.
2. Open any plain-text editor. TextEdit works if you switch it to plain text first (Format → Make Plain Text), or use the editor you already have.
3. Paste the answer.
4. Save the file with a .md ending, for example answer.md or setup-notes.md.

If you paste into a rich-text editor without switching to plain text, it can turn the Markdown into styled text and strip the symbols you need. Plain text keeps the #, *, | and $ intact, which is exactly what the renderer reads.

Files that are already Markdown skip this step. A README.md from a repo or a report an agent saved is ready to open as is.

Open it in Unmarked

Double-click the .md file, or open Unmarked and press ⌘O. Unmarked opens it in the mode you used last (by default). If that's Write, press ⌘E for Read mode, the rendered document with no syntax shown.

The example above now reads as a proper section heading, a numbered list, and a two-column table. Headings, paragraphs, bold and italic, nested lists, blockquotes, links, tables, code and math all render natively.

Code is colored by language. The model usually names the language after the opening fence, like python or bash, and Unmarked colors the block to match. To lift a snippet out, select it in Read mode, or put the cursor inside the block in Write mode and use its copy button.

Math is typeset when it sits between dollar signs ($…$ in a sentence, $$…$$ on its own lines). If an answer wraps math in \( \) or \[ \], Unmarked doesn't read it as math, so ask the assistant to use dollar signs. More on writing math.

If the assistant gave you a checklist, its - [ ] items are real checkboxes in Read mode, and ticking one saves the change back to the file.

Read along while an agent writes

Coding agents often write their plans, reports and docs as Markdown. Open the file in Unmarked and keep the window beside the terminal or chat. As the agent writes, the document fills in with headings, tables and code already rendered, and the part you were reading stays put. What happens when another app changes your file.

A skeleton for saving an AI answer

When you want a clean file to drop an answer into, this structure holds up. Paste the model's text under the relevant heading.

# What I asked
 
A one-line note of the question or task.
 
## The answer
 
Paste the assistant's response here.
 
## Things to try
 
- [ ] First step
- [ ] Second step
- [ ] Third step
 
## Code
 
```bash
# paste any commands the model gave you
```
 
## Source
 
Which assistant, and the date.

Open that in Unmarked and the outline sidebar lets you jump between "What I asked," "The answer," and the rest by heading.

What shows as plain text

Most of what ChatGPT and Claude produce renders directly. A couple of other things show as typed:

• Footnotes ([^1]) appear as the plain text the model wrote.
• Remote images, the kind written as an https:// link, show as their alt text, because Unmarked doesn't fetch anything from the web. That includes README badges that point at a web service. A local image saved next to your file renders normally.

Editing and exporting the answer

Once the answer is in a file, it's yours to keep. Write mode lets you edit it with the formatting in place and the Markdown marks showing only where your cursor is. When you're done, export to PDF, Word or HTML, equations included, or copy as rich text to paste into Mail or Slack.

An AI answer rendering differently than you expect? Email support@untitledapps.dev with the saved .md file and we'll take a look.