> ## Content Index
> Fetch the complete content index at: https://www.gwintrob.com/llms.txt
> Use this file to discover other available public pages before exploring further.

# How I use AI to predict the future
- URL: https://www.gwintrob.com/how-i-use-ai-to-predict-the-future/
- Published: 2025-02-12T15:46:23.000Z
- Updated: 2025-02-23T23:21:16.000Z
- Author: Gordon Wintrob

## The contest

I compete in an annual predictions contest with a group of friends. Each January, we make a series of guesses about the economy, politics, etc. to see who is most accurate at the end of the year. Beyond the cash prize, the winner gets a green Masters jacket and the loser has to give a short presentation on how they made their predictions.

![](https://storage.ghost.io/c/a2/5e/a25e4edc-c102-486a-8e86-aa75eb94a622/content/images/2025/02/image-1.png)

Some of the 2024 predictions.

There are about 60 predictions total and most of the questions come from the [ACX contest](https://www.metaculus.com/tournament/ACX2025/?order%5Fby=-published%5Fat&status=open&page=4&ref=gwintrob.com). For example, “Will Google's search market share drop below 85% in 2025?” or “Will semaglutide be taken off FDA's drug shortage list in 2025?” 

## Making predictions with AI

Last year, I spent a whole weekend researching them and then coming up with a guess (a % chance from 0 to 100). I wanted to find a way to speed this up so I used a few different AI tools. Here’s a high-level overview of how it works:

![](https://lh7-rt.googleusercontent.com/docsz/AD_4nXdHHnVSxvXrMSIndDnricdBsH6DR0ReEVHu73LGLU-J4NZIRQVuswLPtKds9Hz7z1n5mVG0KQZUzyyzZWwXhU7NV5I-OnaXKJjAbPAAFLIBwF4bJOwPPosuo8DcYAZ6VUIWvFfIFg?key=i5YpdIzAAEkjrSrvPabrKWLF)

### Perplexity + Firecrawl for research

First, I used the [Perplexity API](https://docs.perplexity.ai/home?ref=gwintrob.com) with a prompt “You are an expert researcher helping write research reports for predictions for 2025\. Provide detailed reports with citations.” I sent this prompt with each question I needed to forecast, which gave me a detailed report like this:

```
As of January 2025, Google holds a dominant position in the global search engine market across all devices:
- Google's market share is 89.62% [1]
- Bing is the closest competitor with 4.04% [1]
- Yandex has 2.62% and Yahoo has 1.34% [1]
Looking specifically at desktop searches:
- Google has 78.83% market share [3]
- Bing has 12.23% [3]
- Yahoo has 3.07% [3]
…

```

The best part is Perplexity also returns the URLs of the citations. I scraped each of these URLs using the API from [Firecrawl](https://www.firecrawl.dev/?ref=gwintrob.com), a newer YC startup. Firecrawl handles opening each of the URLs, fetching the raw HTML, and turning it into a text format that’s easy for LLMs to digest.

### o3-mini to synthesize

The final, most powerful part was o3-mini, [the latest reasoning model from OpenAI](https://openai.com/index/openai-o3-mini/?ref=gwintrob.com). I gave a [highly detailed prompt](https://github.com/gwintrob/predictions/blob/main/index.py?ref=gwintrob.com#L129) to the API that looked like this:

```
<task>
- Carefully analyze the provided research and citations
- Highlight key factors that could change your estimate
- Provide a specific probability estimate between 0 and 100%. The estimate will be graded using the Brier score
</task>

```

Along with the task definition, I included the Perplexity research report and the Firecrawl-extracted text from all of the citations. o3-mini allows for a \`reasoning\_effort\` setting, which I set to high so that it would spend more time considering how to make the prediction:

```
I estimate there is about a 15% chance that Google’s search market share will drop below 85% in 2025.

```

Each prediction only cost \~5 cents even using the most powerful OpenAI model and only took a few minutes across the research, scraping, and reasoning steps. My Perplexity and Firecrawl usage was within their free allowance. That means the whole project only cost \~$3 for 60 predictions.

## The results

Instead of taking hours of manual research, I let my AI assistant do its thing and make the predictions:

![](https://lh7-rt.googleusercontent.com/docsz/AD_4nXd7XjyVcGahrbqqXU0SIxbaJ3VM_UK9HyNwXJVhDwEb-9W94wHfbM0XTSpLUD2B8XA2uPsrKa27bx8wQp0SSJfZ9VTL4TZxJ8MS0SfKvk5MwTSejWCX2xr3z7_WrEmPtyKsFLGiMQ?key=i5YpdIzAAEkjrSrvPabrKWLF)

### What's next?

Here are some ways I would’ve improved the project:

- I only used a maximum of 10 citations per prediction. Sometimes the Firecrawl data ingestion failed, which meant I’d only have 8 or 9\. It would’ve been interesting to explore using more citations or pushing for more diverse sources.
- I cut off the citations after 2048 characters to make sure that o3-mini had plenty of context for reasoning (its max context window is 128k tokens *including* its internal reasoning). I could’ve experimented with different amounts of text from each citation or trying to only include the most relevant chunks.
- I could’ve written the script to run in parallel. I pulled it together quickly using Cursor with Claude Sonnet 3.5 (the 4th AI in this project 😅)
- OpenAI released [Deep Research](https://openai.com/index/introducing-deep-research/?ref=gwintrob.com) the next day. I would’ve liked to test it out for this use case and compare the results. My initial attempts with Deep Research seemed to pull from less relevant sources than Perplexity.

I look forward to updating this post with a photo of me and my AI pal wearing the winner’s jacket at the end of the year. [Full repo here](https://github.com/gwintrob/predictions?ref=gwintrob.com) in case you’re interested in making your own predictions.