At the beginning of the fantasy football season, I wrote about how to use ChatGPT to generate fantasy football team names and how to use ChatGPT to WIN at fantasy football. Both articles were very popular. With many of the key decisions over the season, I tried to drink my own champaign, so to speak, and leverage ChatGPT to help me make the best choice, overcome my team affinities, and see through the media noise. I used AI effectively. I made it to my league’s championship. I am playing for my first gold trophy, my first championship win. I scored the most fantasy football points through the regular season, earned a first-round bye, and won the semifinal matchup to make it to the finals. Now, I have the daunting task of scoring more points than my opponent this week. I have a solid team, but I have been hit or miss with wide receivers all season. I drafted running backs and Mahomes early, and this has caused a gap in my WR2 and flex spots. Now, I have one spot on my roster that I want to dial in to help give me the edge. It is a decision between George Pickens and DeAndre Hopkins. Both of these players have been hit or miss, but their hits have definitely been hits. I need all my studs to produce, and I need to have some hits in order to finish off the season with the trophy. Here’s my process for figuring out who to start this week in fantasy football.
Will I hoist the gold trophy?
Start by Googling, “DeAndre Hopkins or George Pickens”
I just searched Google for “deandre hopkins or george pickens” and as I typed it out, Google recommended this exact search phrase. I am probably not the only one in this quandary. Google returned some interesting articles.
Based on fantasy football experts weighing the week 17 start decision between DeAndre Hopkins and George Pickens, it is a no-brainer to start DeAndre Hopkins.
My work is done. Thanks for reading.
Wait! I haven’t even used ChatGPT yet in this article, so at least I have to do a little more investigating to make this decision. Remember, the stakes could not be higher in Week 17 of the fantasy football playoffs. I literally either hold up the virtual trophy or get ridiculed for all of the smack I have been dishing all season. I really don’t want my comeuppance.
Use ChatGPT to Get A Second Opinion
Why is this a tough choice for me? Well, DeAndre Hopkins has burned me. I basically started him all season, and he had some stellar games. DeAndre’s last two weeks (weeks 15 and 16) were terrible. He netted 3 points per outing. There are a lot of factors at play here. His team, the Tennessee Titans, is in total chaos with different QBs and key injuries. George Pickens, on the other hand, is playing for a team, The Pittsburgh Steelers, fighting for a lucky wild card spot in the NFL playoffs. The Stillers are in a must-win situation, but the starting QB job for them has been in flux. George has had to take passes with three different starting quarterbacks and play calling from two different offensive coordinators. I am also Pittsburgh-biased. I grew up watching the Steelers with my dad, and I have a deep love for the Black and Gold.
This is where ChatGPT can shine. ChatGPT doesn’t care about my nostalgia, the love of a team, or my enduring faith in anything possible; ChatGPT just tells me how it is.
Let’s start by asking ChatGPT what it needs to help me make this choice.
I am trying to decide between two NFL wide receivers to start in a fantasy football championship game. This is the final game of the season. What information would you like to know to help me make a decision?ChatGPT needs the following information to make the best decision:
- Player Names: Knowing the specific players you’re choosing between will allow me to analyze their recent performance, skill sets, and any relevant news.
- Recent Performance: Information about their performance in recent games, such as receiving yards, touchdowns, targets, and receptions, would be crucial.
- Opposing Teams: Knowing who they will be playing against is important, as some defenses are stronger against wide receivers than others.
- Injury Reports: Any recent injuries or health issues either player has had, as well as their current injury status.
- Weather Conditions: For outdoor games, the weather can impact a wide receiver’s performance, especially in extreme conditions like heavy snow or rain.
- Quarterback Performance: The performance and reliability of their respective quarterbacks, since a wide receiver’s success is often linked to their quarterback.
- Game Stakes: Whether their team is fighting for a playoff spot or in a must-win situation, as this can sometimes influence player performance.
- Historical Performance Against the Opponent: If they have historically performed well or poorly against their upcoming opponent.
- Team Offensive Trends: Whether their team has been more pass or run-heavy in recent games, and any strategic shifts that could impact wide receiver usage.
- Expert Opinions and Analyst Reports: Sometimes, insights from fantasy football experts and analysts can provide additional context or information you might have missed.
This is an impressive list of contexts that ChatGPT is going to need. ChatGPT Plus includes Bing Search. I asked ChatGPT to research each of these for both players. This loads the AI with context so that I can ask ChatGPT to make a decision. This will take some time, as ChatGPT will only look up one player at a time for each dimension.
Research these areas with the following two players: DeAndre Hopkins and George Pickens.ChatGPT started with DeAndre and looked up his 2023 NFL stats using Bing. It returned a short description of his stats. I asked ChatGPT to do this for George Pickens. I had to do this for the other questions. ChatGPT started to focus on the starting quarterback situation for both teams. The Titans have a rookie QB likely to start, and the Steelers have a veteran QB likely to start.
I next asked it about the game stakes. This is an important thing to understand. Do their teams have anything to play for? What is their playoff pictures? Do this prompt for both teams.
Continue with the research.
Research whether the Titans have been more pass or run-heavy in recent games, and any strategic shifts that could impact wide receiver usage.As you are having this conversation with ChatGPT, you are building context that will help inform the decision.
Let’s look up the weather report for the week 17 games. Both games are in the elements. Again, do this for both games.
Let’s use ChatGPT to summarize all of the research in two paragraphs before we ask it to do a comparison and make a decision.
Summarize all of the research that we have gathered so far. Write a paragraph to summarize what you learned for DeAndre Hopkins and George Pickens. Add an introduction restating the decision that we want to make with this research. Keep it short.Here’s a summary of what we are trying to do and what we know so far:
You’re trying to decide between starting DeAndre Hopkins or George Pickens for a fantasy football championship game. For DeAndre Hopkins, his performance with the Tennessee Titans in 2023 has been consistently strong, recording 61 receptions, 939 receiving yards, and 6 touchdowns. He showed significant contributions in key games, especially against defenses that are weaker against the pass. George Pickens, in contrast, has had standout performances, like the one in Week 16 against the Cincinnati Bengals, with 195 receiving yards and 2 touchdowns. Despite less consistency, Pickens has demonstrated the ability to make impactful plays, particularly in downfield passing situations. Both players offer unique strengths: Hopkins with steady performance and experience, and Pickens with potential for high-impact games.
Okay, that is a good summary. Let’s get to the detailed comparison and the decision. A trick that I have learned is to use something called a Pugh chart.
Create a detailed Pugh table showing each player and the relevant dimensions. Fill out the table with the research.| Criteria | DeAndre Hopkins | George Pickens |
|---|---|---|
| Recent Performance | Consistent, with key games showing significant contributions, especially against weaker defenses | Less consistent, but demonstrated potential for high-impact games like Week 16 against the Bengals |
| Opposing Team Defense | Faced a mix of defenses, including weaker ones against the pass | Showed ability to exploit defenses, especially in downfield passing |
| Injury Reports | No significant recent injuries reported | No significant recent injuries reported |
| Quarterback Performance | Quarterback Will Levis shows promise, but is a rookie, potentially affecting consistency | Mason Rudolph has been effective recently, showing a strong connection with Pickens |
| Weather Conditions | Game in Jacksonville; cool and humid, potentially affecting the passing game | Game in Seattle; damp and chilly, might impact the passing game |
| Historical Performance | Strong historical performance, experience in high-stakes games | Less historical data but has shown the ability to make significant plays in crucial games |
And, for the decision:
Be opinionated. Give me a start decision between DeAndre Hopkins and George Pickens based on the research and analysis from this chat. Give me a bullet list for why you would start one player over the other.
ChatGPT chooses George Pickens.
I just changed my starting lineup for the championship. I am going to put my money where my mouth is and use the advice from ChatGPT. DeAndre Hopkins is now on the bench. George Pickens, FTW.
How Do I Feel About This?
As I wrote this blog post and did the research, I had some mixed feelings. ChatGPT, just like me, has recency bias. The last two weeks have been bad for Hopkins, and for one week, George looked phenomenal. AI might be picking up on recent failures and successes and weighting that too much. Maybe ChatGPT is a huge fan of the Steelers like me. ChatGPT was trained on a lot of our text. Surely, there are more Steelers fans in the world than any other sports team. I am in my coozy bubble, I know. Am I cheating? What does it mean to get an edge? Seriously, I would do anything to win this championship. I started playing fantasy football six years ago and got to the championship game to lose at the last minute to like 100 Todd Gurley carries in garbage time. Like I covered in my previous fantasy football posts, I am using this as an opportunity to learn as much as I can about generative AI and ChatGPT. Fantasy football is often about close calls, and stats and context help make tough decisions. I hope this gets you to want to try out ChatGPT or Microsoft Copilot or Google Bard and see what you can learn.
Good luck this week in fantasy. I hope you are playing for the championship and not like those others who are playing for consolation prizes.
Update: December 31, 2023
I woke up to thousands of visits to this blog post. It seems others were researching the decision between George Pickens and DeAndre Hopkins as well. It turns out that the decision to start George Pickens was the correct play. George had a great game, filled with explosive routes, dynamic catches, and stiff blocking. Great game, George.
In other news, I won my championship! I have to admit that I am a bit giddy. Each one of my starts proved to be important. My biggest mistake was starting the Raiders defense instead of Baltimore’s. I lost 20 points on that choice, so I was happy to have had the small advantage of George and Rice to overcome the difference.