OpenAI ChatGPT is a gamechanger for FM immersion

[Smurf]

@enigmatic

For kicks and giggles I asked chatgpt how much it costs for it's API - and it gave me some costs depending how many users would be required. 

It was very interesting - and given that it's data cut off point is 2021.

I figured out through a bit of research there were approximately 1 million sales of Football Manager through most vendors.

Anyway - based on a million people.

If they had 200 api requests a day the cost would be $25 a year per user.

That would have a significant increase in price for the game. 

-------------

 

That being said - I understand the costs risks - but for fun they have a lot more models other than AI chat.

 

DALL-E can generate images - so you could have unique features for players and new faces all the time - unlimited.

Players could get older looking. 

 

Audio

So you could generate live commentary of the matches with unique commentary and listen to the commentary like you would a real match.

It would be a unique experience each time. 

Imagine licensing Roy Keane's voice to give a pundit response in video/audio to a game or something like that.

 

-------------

 

Aside from costs - which i agree at the moment are probably unfathomable - 

It opens up a pretty unique opportunity for what is already considered the most realistic football manager simulation of all time. 

 

I'm a little bit excited about it. 

Perhaps pricing will come down over the years. 

But seriously sounds like a very interesting proposal.

 

• AI chat with staff/players for more immersive experience
• Generate life like photos of players and age them as time goes on. 
• Real time commentary of matches with unique experience each time
• Generate video clips/commentary audio that are realistic and unique

I know you will probably say you're not interested in all that - which is fine. But others are interested. 

This game could actually be closer to real life than ever before.

 

Anyway - just thought I'd throw out some of those things.

 

 

 

 

[Mars_Blackmon]

Edited March 6, 2023 by Mars_Blackmon

[Mars_Blackmon]

On 05/03/2023 at 02:19, Smurf said:

@enigmatic

For kicks and giggles I asked chatgpt how much it costs for it's API - and it gave me some costs depending how many users would be required. 

It was very interesting - and given that it's data cut off point is 2021.

I figured out through a bit of research there were approximately 1 million sales of Football Manager through most vendors.

Anyway - based on a million people.

If they had 200 api requests a day the cost would be $25 a year per user.

That would have a significant increase in price for the game. 

-------------

 

That being said - I understand the costs risks - but for fun they have a lot more models other than AI chat.

 

DALL-E can generate images - so you could have unique features for players and new faces all the time - unlimited.

Players could get older looking. 

 

Audio

So you could generate live commentary of the matches with unique commentary and listen to the commentary like you would a real match.

It would be a unique experience each time. 

Imagine licensing Roy Keane's voice to give a pundit response in video/audio to a game or something like that.

 

-------------

 

Aside from costs - which i agree at the moment are probably unfathomable - 

It opens up a pretty unique opportunity for what is already considered the most realistic football manager simulation of all time. 

 

I'm a little bit excited about it. 

Perhaps pricing will come down over the years. 

But seriously sounds like a very interesting proposal.

 

• AI chat with staff/players for more immersive experience
• Generate life like photos of players and age them as time goes on. 
• Real time commentary of matches with unique experience each time
• Generate video clips/commentary audio that are realistic and unique

I know you will probably say you're not interested in all that - which is fine. But others are interested. 

This game could actually be closer to real life than ever before.

 

Anyway - just thought I'd throw out some of those things.

 

 

 

 

 

[Smurf]

On 07/03/2023 at 02:12, Mars_Blackmon said:

 

Interesting. Not done extremely well - but interesting.

 

[Mars_Blackmon]

 

Good to see videos showing people doing exactly what I described in my post months ago.

When it comes to computer language, it is important to "prompt" rather than being vague. A vague statement opens the door for things to go wrong. It is similar to the peanut butter and jelly challenge. 

I learned as a Computer Science major that computers are useless, they only provide you with answers. Garbage goes in, garbage comes out.

 

As for integrating Chat GPT into the game for things like the press, eventually, this will be the technology whether it be chat gpt or something else but we aren't there yet, however, chat gpt can be used today to get a lot more variety in a quicker amount of time in the text document for interviews, player interactions, and news stories so these areas won't be repetitive.

 

Edit- Here’s a good article on prompting 

https://dataconomy.com/2023/01/what-is-ai-prompt-engineering-examples-how/

Edited April 3, 2023 by Mars_Blackmon

[Gangor]

On 05/03/2023 at 07:19, Smurf said:

@enigmatic

For kicks and giggles I asked chatgpt how much it costs for it's API - and it gave me some costs depending how many users would be required. 

It was very interesting - and given that it's data cut off point is 2021.

I figured out through a bit of research there were approximately 1 million sales of Football Manager through most vendors.

Anyway - based on a million people.

If they had 200 api requests a day the cost would be $25 a year per user.

That would have a significant increase in price for the game. 

-------------

 

That being said - I understand the costs risks - but for fun they have a lot more models other than AI chat.

 

DALL-E can generate images - so you could have unique features for players and new faces all the time - unlimited.

Players could get older looking. 

 

Audio

So you could generate live commentary of the matches with unique commentary and listen to the commentary like you would a real match.

It would be a unique experience each time. 

Imagine licensing Roy Keane's voice to give a pundit response in video/audio to a game or something like that.

 

-------------

 

Aside from costs - which i agree at the moment are probably unfathomable - 

It opens up a pretty unique opportunity for what is already considered the most realistic football manager simulation of all time. 

 

I'm a little bit excited about it. 

Perhaps pricing will come down over the years. 

But seriously sounds like a very interesting proposal.

 

• AI chat with staff/players for more immersive experience
• Generate life like photos of players and age them as time goes on. 
• Real time commentary of matches with unique experience each time
• Generate video clips/commentary audio that are realistic and unique

I know you will probably say you're not interested in all that - which is fine. But others are interested. 

This game could actually be closer to real life than ever before.

 

Anyway - just thought I'd throw out some of those things.

 

 

 

 

I asked about FM too and while it thinks a large language model wouldn't be practical, is suggested that a more tightly designed language model designed for generating specific types of text (like football interviews etc) might work on consumer hardware

[JamieTC13]

On 07/03/2023 at 02:12, Mars_Blackmon said:

 

This can make the game very immersive and if done right this could be brilliant. I like this idea a lot

[Mars_Blackmon]

32 minutes ago, JamieTC13 said:

This can make the game very immersive and if done right this could be brilliant. I like this idea a lot

Yea, LLM will eventually make its way into video games, the question is when and how.

[Platinum]

20 hours ago, Mars_Blackmon said:

however, chat gpt can be used today to get a lot more variety in a quicker amount of time in the text document for interviews, player interactions, and news stories so these areas won't be repetitive.

Yep agreed, probably not cost effective, but purely from a users point of view it will bring much more variety.

Would have to testing around how often it adds things that aren't factual /true though

[WizbaII]

The chatting AI's responses are undoubtedly impressive, and I can understand what all the fuss is about. Based on what I read in the previous posts, it has the ability to produce responses that only a football expert would find generic.

However, as far as FM goes, AI will not be truly revolutionary until it learns to write code, or at least can be trained to analyze which parts of the ME are best and worst in replicating real football. When AI can have a significant effect on the ME itself, then I'll be truly intrigued.

[jmb1403]

I thought this was interesting:

[Gangor]

22 hours ago, jmb1403 said:

I thought this was interesting:

Weird, it made a tactic for me the other day. I asked it a bunch of questions and it justified its choices for player instructions etc

Edited April 7, 2023 by Gangor

[Mars_Blackmon]

11 hours ago, Gangor said:

Weird, it made a tactic for me the other day. I asked it a bunch of questions and it justified its choices for player instructions etc

It’s can’t come up with an original the tactic of its own. It is not AI that can think for itself. We aren’t there yet with AI. We are still in data learning phase of AI. It’s been trained on data points up until 2021 which includes and not limited to forums. In short, it is regurgitating information that is already known.

[Gangor]

1 hour ago, Mars_Blackmon said:

It’s can’t come up with an original the tactic of its own. It is not AI that can think for itself. We aren’t there yet with AI. We are still in data learning phase of AI. It’s been trained on data points up until 2021 which includes and not limited to forums. In short, it is regurgitating information that is already known.

It does base its output on information it's been trained on, but it's not just regurgitating that information, it's distilling it.  The tactics it creates (as far as I can see) aren't particularly clever and probably wouldn't even work well within the game engine; it's not designed for things like this. But still the fact that it can come up with tactics is impressive.

[Mars_Blackmon]

1 hour ago, Gangor said:

It does base its output on information it's been trained on, but it's not just regurgitating that information, it's distilling it.  The tactics it creates (as far as I can see) aren't particularly clever and probably wouldn't even work well within the game engine; it's not designed for things like this. But still the fact that it can come up with tactics is impressive.

If you know what to ask it, the tactics are perfectly fine. Is it going to create OP or RDF tactics? No. But probably or par or even better than the presets in the game. I’m sure majority of it’s information comes from the game and official guides so it’s not going to “bend” the match engine.

Edited April 7, 2023 by Mars_Blackmon

[Mars_Blackmon]

 

[Mars_Blackmon]

He imported his exported data for his team in German, creating a specific tactic. I hinted at this months ago.

Edited April 7, 2023 by Mars_Blackmon

[Panosgeo79]

Just to add, this ChatGPT and the following relatives,will change the world as we know it.

We are only in the beginning.

Game industries will be a massive upgrade especially dealing with NPC ,dynamic scenarios , different paths and many more.

Things we we cant even imagine.

SI must and should catch the speed of it otherwise will be catched by some other relative company.

The potentials are limitless especially for games like FM

[Mars_Blackmon]

9 hours ago, Panosgeo79 said:

Just to add, this ChatGPT and the following relatives,will change the world as we know it.

We are only in the beginning.

Game industries will be a massive upgrade especially dealing with NPC ,dynamic scenarios , different paths and many more.

Things we we cant even imagine.

SI must and should catch the speed of it otherwise will be catched by some other relative company.

The potentials are limitless especially for games like FM

I agree, companies are already integrating it. Bing has it integrated with its search engine. If anything, SI could use this technology to improve the assistant manager.

[Panosgeo79]

For example yesterday i asked GPT to create a guide for my beloved 433 DM system,roles ,pairings etc

You cant even believe how much details has put in it.

Just check for yourself with the right questions.

And all these.without.even scratching GPT 4 or at the end of the year GPT 5...

FM 25 would be most probably amazing.

Ofcourse there js a chance that we could be servants of AI untill then😀

 

[themadsheep2001]

As discussed back on page 2 it's pseudo knowledge. It has no access to, and therefore no context of the match engine. Much like when someone asked it to build a tactic based on Sir Alex Ferguson. It would be useful for generating text flavour. But not as an information tool in FM. 

[XaW]

I really wish people would understand the difference between things like this and actual AI. ChatGPT is essentially an interactive encyclopedia, but it is a fun one. It can not understand the answer it gets or the context around it, as it will tell you if you ask it.

So while it does seem fun and that you can interact with it, it's just using patterns to find the best answer rather than any intuitive intelligence.

As for FM and using it, I think it could be viable as a help tool since SI could control the base data it uses. Not sure if that is good return on the investment it would require though, but I don't know how that business case would look, so it's just a guess.

[forameuss]

But people told me that if SI didn't immediately jump on this yesterday then they'd almost certainly be winding up the company and the product by next week?  

I'm still yet to see any use case put forward that would really add a whole lot to the game as things stand.  There's probably core concepts in there that could be adapted and followed up on by SI with a more tailored solution, but then those things were probably already on the table already.  An interactive encyclopedia finding a hundred more ways to say the same thing isn't going to bring as much to the game as improving the original thing in the first place.

Edited April 18, 2023 by forameuss

[Panosgeo79]

22 hours ago, themadsheep2001 said:

As discussed back on page 2 it's pseudo knowledge. It has no access to, and therefore no context of the match engine. Much like when someone asked it to build a tactic based on Sir Alex Ferguson. It would be useful for generating text flavour. But not as an information tool in FM. 

i agree on this

but its the beginning as I said

he can surely help you better than FM assistant managers or 50% of FM gamers.

And its the GPT3.5...

Edited April 19, 2023 by Panosgeo79

[Mars_Blackmon]

 

The paid version of GPT4 has added a few tools since April. One that stands out is the data analysis tool. Using the tool, I gave it an Excel file, and asked it to create a tactic suitable for the team. I made some adjustments but definitely a good starting point and more personalized to your team vs. the preset tactics.

 

Quote

Great, we've successfully loaded the data this time! The dataset is quite comprehensive and includes various attributes for each player on the Oxford City team, based on Football Manager 2023 data.

Here are some of the key columns:
- **Position Selected**: The position the player is primarily chosen for.
- **Name**: Player's name.
- **Age**: Player's age.
- **Nat**: Nationality.
- **Club**: The club they play for (Oxford City in this case).
- **On Loan From**: The club the player is loaned from, if applicable.
- **Position**: The player's primary position.
- **Sec. Position**: The player's secondary position.
- **Player Status**: Any special status for the player like 'Wnt - Rst' (Wanted - Rest).
- **Preferred Foot**: The foot the player prefers to use.
- **Height, Weight**: Physical attributes.
- **Various Skill Ratings (e.g., Acc, Aer, Agg)**: Ratings for different skills and attributes.
- **Wage, Value**: Financial details.
- **Transfer Status, Asking Price**: Transfer-related information.
- **Home-Grown Status**: Whether the player is home-grown or not.

Would you like to focus on any specific aspect for the team analysis? For example, we could look at:
1. Overall team strength based on skill ratings.
2. Age distribution.
3. Strengths and weaknesses in specific positions.
4. Financial aspects like wage distribution and player values.

Please let me know how you would like to proceed!

Quote

### Overall Team Strength Based on Skill Ratings

Here's how Oxford City fares in various skills, based on the mean ratings of all players in the team:

#### Top 5 Strengths:
1. **Natural Fitness (Nat.1)**: 11.0
2. **Aggression (Agg)**: 10.2
3. **Acceleration (Acc)**: 9.9
4. **Jumping Reach (Jum)**: 9.7
5. **Pace (Pac)**: 9.2

#### Bottom 5 Skills:
1. **Eccentricity (Ecc)**: 2.4
2. **One on Ones (1v1)**: 2.4
3. **Throwing (Thr)**: 2.5
4. **Communication (Com)**: 2.6
5. **Kicking (Kic)**: 2.8

#### Observations:
- The team excels in physical attributes like natural fitness, acceleration, and pace, which suggests that they would be well-suited for a high-tempo, pressing game.
- The team also has a high mean rating for aggression, indicating a potentially aggressive playstyle.
- However, the team seems to lack in more specialized skills like eccentricity, one-on-ones, and throwing. 

Would you like to dive deeper into any of these aspects, or would you like to explore something else?

Quote

Creating a tactic in Football Manager 2023 involves various aspects like formation, player roles, team instructions, and set-piece strategies. Based on the Oxford City team's strengths and weaknesses, here's a suggested tactic.

### Formation: 4-2-3-1 High Press

#### Why 4-2-3-1?
- This formation allows the team to make the most of their physical attributes like pace, acceleration, and natural fitness.
- It provides a good balance between defense and attack.
- Utilizes wide players, which is beneficial given the team's strengths in acceleration and pace.

#### Player Roles:

- **GK (Goalkeeper)**: Standard Goalkeeper
- **RB & LB (Full-backs)**: Wing-Backs (Support) — to make use of their good acceleration and pace.
- **CBs (Centre-backs)**: Ball-Playing Defenders — to initiate play from the back.
- **CDM (Central Defensive Midfield)**: Deep-Lying Playmaker (Defend) and Ball-Winning Midfielder (Support)
- **CAM (Central Attacking Midfield)**: Advanced Playmaker (Attack) — to make use of their creativity and vision.
- **LM & RM (Left and Right Midfield)**: Wingers (Attack) — to capitalize on their pace and crossing ability.
- **ST (Striker)**: Complete Forward (Support) — a versatile role that can drop deep, lay off passes, or go for goal.

#### Team Instructions:

- **Mentality**: Positive
- **In Possession**: Higher Tempo, Play Out of Defense, Use Offside Trap
- **In Transition**: Counter-Press, Counter
- **Out of Possession**: Use Offside Trap, Higher Line of Engagement, Higher Defensive Line

#### Set-Piece Strategies:
- **Corners**: Aim for the near post as the team has good aggression and jumping reach.
- **Free Kicks**: Mixed delivery to make use of the team's aggression and heading ability.

#### Strengths:

- The tactic makes full use of the team's high natural fitness, aggression, and work rate.
- The high press and counter-press suit the team's overall aggressive nature.
  
#### Weaknesses:

- The high line could be vulnerable to long balls and pacey strikers, so the central defenders should be cautious.

Would you like to know more about how to implement this tactic in Football Manager 2023?

 

[The3points]

I think the tactic is quite poor to be honest. Ignoring the errors such as the winger being in left and right midfield, the duplication of offside trap, higher line of engagement for FM23 etc. the tactic just doesn't work that well. The tactic has almost the exact same qualities up the right as up the left, 3 out of the front four are on attack, both fullbacks move forward and this is all with Oxford City, a National League South team. While more "personalised" than the preset, I think it's not the best tactic for general use.

[Mars_Blackmon]

52 minutes ago, The3points said:

I think the tactic is quite poor to be honest. Ignoring the errors such as the winger being in left and right midfield, the duplication of offside trap, higher line of engagement for FM23 etc. the tactic just doesn't work that well. The tactic has almost the exact same qualities up the right as up the left, 3 out of the front four are on attack, both fullbacks move forward and this is all with Oxford City, a National League South team. While more "personalised" than the preset, I think it's not the best tactic for general use.

I didn't share the entire chat. The wingers are attacking midfielders, hence, the formation and the offside trap duplication were fixed. The adjustments I made were only using one BPD. Other than that, not only did we win the league during a simulation to test the tactic, but the tactic scored five stars on ratemytactic after the adjustment with the BPD. 

Ratemytactic is another tool that can help with tactics, but that was used to make sure that penetration, support, and solidity all scored well. So it did work well logically.

[The3points]

These were the results I got.

Then after BPD adjustment.

Never mind the fact that symmetrical roles in tactics isn't the best

[Mars_Blackmon]

2 hours ago, The3points said:

These were the results I got.

Then after BPD adjustment.

Never mind the fact that symmetrical roles in tactics isn't the best

This is the actual tactic. I forgot that I also changed the AP from attack to support. Counter press and Counter were removed as GPT mentioned that they should be situational after I raised the conflicting error. It's the same with the offside trap after I told it about the updated strategies for the offside trap in the game.

 

Also, this is without going deep into each player and their best roles. So, a CF or even a BPD at the lower league most likely wouldn't have been suggested if I got even more detailed.

I loaded an Excel file and told it to show strengths and weaknesses. (You have to ask GPT to exclude the GK as it will factor their attributes in the overall average and vice versa for the GK attributes for the team; You could go deeper than that and separate each position like defender, midfield, and attack.) Then, ask it to create a suitable tactic. Then, we fixed any errors.

This is data-driven. The better data and prompts you put in, the better results. People seem to expect GPT to have its own AI brain and are quick to point out any errors....

 

Edited October 4, 2023 by Mars_Blackmon

[enigmatic]

tbh it looks like a pretty standard gegenpress you could find in these forums, or any third-party site (in downloadable form) with added nonsense related to your statistics (nothing wrong with mixed set piece delivery, but the average aggression rating of the team has nothing to do with whether it's the right option or not). 

Suggesting the team lacks eccentricity and that you should use an offside trap in possession gives you an idea of how good the tactical insight actually is. 

When SI's tooling gives crap recommendations like that I file bug reports, and whilst they don't always fix the bugs at least they actually can...

 

[Mars_Blackmon]

4 minutes ago, enigmatic said:

tbh it looks like a pretty standard gegenpress you could find in these forums, or any third-party site (in downloadable form) with added nonsense related to your statistics (nothing wrong with mixed set piece delivery, but the average aggression rating of the team has nothing to do with whether it's the right option or not). 

Suggesting the team lacks eccentricity and that you should use an offside trap in possession gives you an idea of how good the tactical insight actually is. 

When SI's tooling gives crap recommendations like that I file bug reports, and whilst they don't always fix the bugs at least they actually can...

 

Eat the meat, spit out the bones.

[enigmatic]

10 minutes ago, Mars_Blackmon said:

Eat the meat, spit out the bones.

More just because you're getting nuggets doesn't mean there was ever any chicken involved 

[Mars_Blackmon]

15 minutes ago, enigmatic said:

More just because you're getting nuggets doesn't mean there was ever any chicken involved 

Nuggets don’t have bones

[enigmatic]

1 minute ago, Mars_Blackmon said:

Nuggets don’t have bones

Neither do LLMs  

[Mars_Blackmon]

41 minutes ago, enigmatic said:

Neither do LLMs  

But even an LLM knows to distinguish between accurate and false information when prompted...

 

At the end of the day, it's a tool. and with tools and machines, it's always the person behind it, not the tools itself.

Edited October 4, 2023 by Mars_Blackmon

[enigmatic]

28 minutes ago, Mars_Blackmon said:

At the end of the day, it's a tool. and with tools and machines, it's always the person behind it, not the tools itself.

I agree with that much  

It's just a tool that's supposed to give you tactical advice that's mostly wrong unless you're advising it isn't a particularly useful tool!

[Mars_Blackmon]

2 hours ago, enigmatic said:

I agree with that much  

It's just a tool that's supposed to give you tactical advice that's mostly wrong unless you're advising it isn't a particularly useful tool!

I'm not going to argue with your opinion. Especially since you are ignoring the concept of input = output.

Edited October 4, 2023 by Mars_Blackmon

[The3points]

6 hours ago, Mars_Blackmon said:

This is the actual tactic. I forgot that I also changed the AP from attack to support. Counter press and Counter were removed as GPT mentioned that they should be situational after I raised the conflicting error. It's the same with the offside trap after I told it about the updated strategies for the offside trap in the game.

 

Also, this is without going deep into each player and their best roles. So, a CF or even a BPD at the lower league most likely wouldn't have been suggested if I got even more detailed.

I loaded an Excel file and told it to show strengths and weaknesses. (You have to ask GPT to exclude the GK as it will factor their attributes in the overall average and vice versa for the GK attributes for the team; You could go deeper than that and separate each position like defender, midfield, and attack.) Then, ask it to create a suitable tactic. Then, we fixed any errors.

This is data-driven. The better data and prompts you put in, the better results. People seem to expect GPT to have its own AI brain and are quick to point out any errors....

 

Sure, but at that point you've changed almost half the tactic: 2 FBs, 1 CB, 1 CAM, 3 instructions. Realistically chatGPT isn't the resource of choice you would use for this sort of thing,

[Mars_Blackmon]

1 hour ago, The3points said:

Sure, but at that point you've changed almost half the tactic: 2 FBs, 1 CB, 1 CAM, 3 instructions. Realistically chatGPT isn't the resource of choice you would use for this sort of thing,

I changed 1 BPD to a CD (Even though 2 BPD works well in the game, ratemytatcic doesn't like it), and I changed the CAM from attacking to support. That's hardly half the tactic. the offside trap works, but I was suggested to use it situationally. Same with counter and counter press. But we all know that pretty much works with any high-press tactic.

Most importantly, no one is forcing you to use it.

[forameuss]

15 hours ago, enigmatic said:

tbh it looks like a pretty standard gegenpress you could find in these forums, or any third-party site (in downloadable form) with added nonsense

Which is basically what GPT is.  It's going out and assimilating all the information it can find and putting together an answer, exactly the same as any human person would do, but "quicker".  Only it doesn't have that extra layer of "wait, is this bs?", so is well capable of parroting back popular but ultimately wrong information.  

It was cool tech, and it's probably going to be a basis of some even cooler stuff in future, but if we're still talking about it's relevance relating to FM, nothing has changed since this thread was started.  It's still not doing anything particularly groundbreaking or useful.

[themadsheep2001]

15 hours ago, enigmatic said:

I agree with that much  

It's just a tool that's supposed to give you tactical advice that's mostly wrong unless you're advising it isn't a particularly useful tool!

Exactly. If people actually want this to be good, they need to accept where its rubbish so it can improve, not stick tneir fingers in their ears. 

In terms of FM,  its still not good enough to be anywhere near the game. 

[diLLa88]

3 hours ago, forameuss said:

Which is basically what GPT is.  It's going out and assimilating all the information it can find and putting together an answer, exactly the same as any human person would do, but "quicker".  Only it doesn't have that extra layer of "wait, is this bs?", so is well capable of parroting back popular but ultimately wrong information.  

It was cool tech, and it's probably going to be a basis of some even cooler stuff in future, but if we're still talking about it's relevance relating to FM, nothing has changed since this thread was started.  It's still not doing anything particularly groundbreaking or useful.

I'm going to test it for using it as a scouting tool where I'll be uploading an excel file with my scouted players list and let it analyse on multiple levels to see whether i can find the right players for the right position.

[Mars_Blackmon]

6 hours ago, themadsheep2001 said:

Exactly. If people actually want this to be good, they need to accept where its rubbish so it can improve, not stick tneir fingers in their ears. 

In terms of FM,  its still not good enough to be anywhere near the game. 

Yet you continue to add nothing to the thread but give an opinion on how wrong someone is instead of trying to come up with better prompts.

[themadsheep2001]

13 minutes ago, Mars_Blackmon said:

Yet you continue to add nothing to the thread but give an opinion on how wrong someone is instead of trying to come up with better prompts.

There are no better prompts, the software isnt smart enough, doesn't sort through whether information it dregdes up is good enough and doesn't understand FM in any context. Nothing has changed since the topic was started in this regards. 

[Mars_Blackmon]

7 hours ago, themadsheep2001 said:

There are no better prompts, the software isnt smart enough, doesn't sort through whether information it dregdes up is good enough and doesn't understand FM in any context. Nothing has changed since the topic was started in this regards. 

Great insight. Your choice of words shows that you have no idea what you are talking about. The concept of prompting is to get clear, relevant information back. "Smart enough." It doesn't think or come up with its own ideas, and for some reason, you keep bringing up the point. You're trying to make a straw man argument. It functions based on patterns learned from the data it was trained on or now with GPT4, the internet. It filters through the data it has learned from or retrieved. It predicts the next word based on the input prompt, trying to generate coherent and contextually relevant text based on the parameters of the prompts, which is similar to coding but in natural language.

Edited October 5, 2023 by Mars_Blackmon

[themadsheep2001]

39 minutes ago, Mars_Blackmon said:

Great insight. Your choice of words shows that you have no idea what you are talking about. The concept of prompting is to get clear, relevant information back. "Smart enough." It doesn't think or come up with its own ideas, and for some reason, you keep bringing up the point. You're trying to make a straw man argument. It functions based on patterns learned from the data it was trained on or now with GPT4, the internet. It filters through the data it has learned from or retrieved. It predicts the next word based on the input prompt, trying to generate coherent and contextually relevant text based on the parameters of the prompts, which is similar to coding but in natural language.

"It doesnt think or come up with its own ideas"  - thats precisely the problem. 

"The concept of prompting is to get clear, relevant information back" again it doesn't give back clear relevant information. Thus it fails at its task here

I'm not the only person to have pointed it out, but you seem intent on ignoring this so i will spell it out clearly, since you still havent grasped it

It cannot advise clearly, since the tactics it offers up are inherently flawed. Because it cannot actually properly filter out good information from bad well enough. And since it has no connection to the game it has no true context to place its data around. In terms of FM usage it is still rubbish. Thankfully SI haven't put it anywhere near FM and thats a good thing. 

[Mars_Blackmon]

7 minutes ago, themadsheep2001 said:

"It doesnt think or come up with its own ideas"  - thats precisely the problem. 

"The concept of prompting is to get clear, relevant information back" again it doesn't give back clear relevant information. Thus it fails at its task here

I'm not the only person to have pointed it out, but you seem intent on ignoring this so i will spell it out clearly. 

It cannot advise clearly, since the tactics it offers up are inherently flawed. Because it cannot actually properly filter out good information from bad well enough. And since it has no connection to the game it has no true context to place its data around. In terms of FM usage it is still rubbish. Thankfully SI haven't put it anywhere near FM and thats a good thing. 

Again, straw man arguments.

 

And the examples I posted here weren't exactly prompted right, which I have pointed out multiple times. It doesn't need to know the game because the data it gets is from sources that played it. A good prompt adds context. I echo that you don't know what you are talking about. 

Edited October 5, 2023 by Mars_Blackmon

[themadsheep2001]

3 minutes ago, Mars_Blackmon said:

Again, straw man arguments.

 

And the examples I posted here weren't prompted right, which I have pointed out multiple times. I echo that you don't know what you are talking about. 

I dont think you know what a straw man argument is. The context here is whether GPT can offer working well thought out tactics from prompts. 

It cannot, thus it fails at being a useful tool for FM. You can echo all you like, but its been repeatedly demonstrated it offers up flawed tactics. 

[Mars_Blackmon]

\

1 minute ago, themadsheep2001 said:

I dont think you know what a straw man argument is. The context here is whether GPT can offer working well thought out tactics from prompts. It cannot, thus it fails at being a useful tool for FM. You can echo all you like, but its been repeatedly demonstrated it offers up flawed tactics. 

You are arguing a point that I have not made.  Your man problem is that it doesn't know FM or think for itself. You made that point multiple times in here, and no, but you mentioned that.

Edited October 5, 2023 by Mars_Blackmon

[Mars_Blackmon]

3 minutes ago, themadsheep2001 said:

I dont think you know what a straw man argument is. The context here is whether GPT can offer working well thought out tactics from prompts. It cannot, thus it fails at being a useful tool for FM. You can echo all you like, but its been repeatedly demonstrated it offers up flawed tactics. 

Do you know people are getting paid lots of money for prompt engineering? You can't prompt right. It is a personal problem. Many people use the tool for FM without any problems, and others use it for way more complex things than video games.