Created a MMA fight Picker GPT

This is the first time it went below chance right? Still scary so far though, might be a stupid question but can one ask the gpt about its process for picking fights, like does it have some kind of technical analysis or narrative for how fights are likely to go based on past PBPs of the fighters or does it just look at numbers?
 
hymn said:
This is the first time it went below chance right? Still scary so far though, might be a stupid question but can one ask the gpt about its process for picking fights, like does it have some kind of technical analysis or narrative for how fights are likely to go based on past PBPs of the fighters?
Click to expand...

I reckon it's lack of data on a bunch of rookies.

I imagine the story is the same next week.

These cards are too low level for accurate metrics.
 
might need to move to Claude3 for the predictions in the future, as opanAI seems to be degrading.
 
Siver! said:
I reckon it's lack of data on a bunch of rookies.

I imagine the story is the same next week.

These cards are too low level for accurate metrics.
Click to expand...
It literally just uses news articles to form opinions if there are no statics to go off.

In the case of MVP vs Holland, it would have seen something like: MVP mentioned multiple times in news articles across the course of his career as being "in the conversation for the greatest striker in the world", versus Holland, who is criticized multiple times in fight reports as having been exploited and having shown a weakness on the ground; and concluded "Holland is not likely to pursue a ground fight as it is not in his repertoire, therefore he is likely to lose to the better striker, who has at times been mentioned in the conversation for best striker in MMA".

Source: I asked it questions when I was using it previously.
 
TSaL said:

UFC Fight Night: Ribas vs. Namajunas​


So OpenAI mygpts have been getting shitter and shitter. I have tried to recreate the gpt a bunch of time and after a few requests it starts to lose it instructions.

For this weeks pick I use Google Gemini 1.5 pro

You can try it here for free:
t.co

Google AI Studio | Google AI for Developers

t.co t.co
Click to expand...
It’s probably my fault. Our robot overlord went 11-3 before I started putting money on its picks. I’ll take a crack at the picks That Gemini gave us just to see how they do
 
I think the card where Yves Edwards KO'd Jeremy Stevens was an all finish card. I can't check right now though.
dog y said:
Has there ever been a card with no decisions?
Click to expand...
Roop Holstry said:
There was a couple in the modern era I think but I can’t recall which ones.

There was also UFC 76: Knockout which featured 0 knockouts and had three subs and the rest were decisions.
Click to expand...
 
hymn said:
This is the first time it went below chance right? Still scary so far though, might be a stupid question but can one ask the gpt about its process for picking fights, like does it have some kind of technical analysis or narrative for how fights are likely to go based on past PBPs of the fighters or does it just look at numbers?
Click to expand...
Below chance is not a good baseline for a sports-betting model though. It should be compared to the baseline of always picking the betting favorite IMO. That would probably get you close to 70% already. Even then, for actual betting it would be better if it spit out the chance of a fighter winning. Because then you could pick a strategy based on model's odds vs. bookmaker odds.
 
Ramon Antonio said:
Below chance is not a good baseline for a sports-betting model though. It should be compared to the baseline of always picking the betting favorite IMO. That would probably get you close to 70% already. Even then, for actual betting it would be better if it spit out the chance of a fighter winning. Because then you could pick a strategy based on model's odds vs. bookmaker odds.
Click to expand...
Betting on the favourite works at in 64% for UFC cards in 2024 vs 68% for TSaL, but 78% before last two FNs
 
TSaL said:
Welp that sucked. I think I will hold off on posting more predictions till I think I have a model that works better. Sorry guys I'll keep trying.
Click to expand...
I still believe in you, this is a great idea,
You’ll get it all sorted
 
You must log in or register to reply here.

Similar threads

TSaL
UFC 297 Fight Analyst Advanced GPT Fight picks
2 3
Replies
44
Views
2K
Portland8242
Portland8242

Latest posts

Forum statistics

Threads
1,237,138
Messages
55,469,477
Members
174,787
Latest member
Biden's Diaper

Share this page

Back
Top