I remember when this was a joke, back in the (mumble decade)*1. We all thought the future would be better because hard tasks would be done by machines.
We expected we would just push a button and get what we wanted. We didn’t expect this to be entirely pain-free. In fact, in one episode, Jane Jetson suffered from “push button finger”. The manual labor of housework required her to push a button so many times her finger hurt from it!
Today, I have push button fingers, plural, that is, all my fingers are suffering from typing on the “buttons” of my keyboard.
Back in the (mumble decade), we thought automation would be A Good Thing, and for decades now, it has been relatively good, as automation replaced hard manual labor.
Back then, computer scientists were hard at work on artificial intelligence. Thinking was that the human brain was a logic machine, and if you could just duplicate that in silicon, the machine could think, too. Just like a human.
Over the years, machines did get more intelligent. Not really to the level of humans. Not to the level of mice, really, but more intelligent than stones. Computer scientists helped computers store large knowledge bases. They improved the ability of computer programs to conceptualize. We got them to solve puzzles more quickly.
Meanwhile, computers got bigger and faster. They got more parallel. They got new techniques for machine learning and Bayesian probability, which allows advanced inference. They got neural networks.
Now, computer scientists have put this together with information available on the Internet to create enormous knowledge bases. This is paired with advanced deduction to form generative AI.
With generative AI, companies can plausibly simulate many human acts of creativity. I’ve used generative AI to create illustrations to market my own creative work, for example. But someone could now plausibly use generative AI to create my work.
I could be replaced by a button.
Specifically, the Enter button on someone’s keyboard, after they’ve typed in a prompt.
Should we allow that? Here’s the downside. It threatens to eliminate jobs for entire swaths of creative artists. Specifically, it might eliminate screenwriters and screen actors. (Not to mention playwrights, directors, graphic artists, songwriters, fine artists, and many others that currently give meaning to life.)
That’s one of the very important reasons WGA and SAG-AFTRA*2 are on strike against the AMPTP*3. The association of producers wants complete freedom to use AI to replace writers and actors.
In normal times, the AMPTP agrees with the WGA to minimum stipulations for contracts. On the writers’ side, these are called MBAs (Minimum Basic Agreements). The WGA proposed in negotiations the following terms:
Regulate use of artificial intelligence on MBA-covered projects: AI can't write or rewrite literary material; can't be used as source material; and MBA-covered material can't be used to train AI.
The AMPTP rejected this proposal and countered with a proposal to “discuss” advancements in technology, annually.
Is the WGA proposal reasonable?
Scott Myers*4, a recent speaker at the Willamette Writers Conference and a member of WGA, investigated. Perhaps WGA could have a more appropriate, reasonable proposal. So, he asked ChatGPT about this:
One of the big issues is the use of AI as part of the process in developing and producing TV episodes and movies. Writers are concerned about AI's impact on how we do their jobs and potential loss of work due to reliance on AI. Are there any guardrails the guilds could negotiate with the studios?
[In this section, I’ve edited these exchanges for brevity, but the full text follows at the end of this article.]
ChatGPT responded:
As an AI language model, I don't have real-time information, and my knowledge is up to September 2021. However, I can suggest some potential guardrails negotiators could propose concerning the use of AI in the creative process:
- Human Oversight: Ensure that AI is used as a tool to assist writers rather than replace them. Propose a requirement for human oversight in all AI-assisted processes to maintain the creative input and vision of writers.
- Fair Compensation and Job Security: Negotiate for fair compensation and job security for writers in instances where AI is implemented. Writers could receive additional compensation for the use of their work in AI-generated content and provisions to protect against job losses due to over-reliance on AI.
- Creative Control: Establish clear guidelines that maintain the creative control of writers over their work when AI is involved. This could include safeguarding against significant alterations or unauthorized use of writers' content.
- Transparency and Accountability: Demand transparency from studios and streaming services regarding the use of AI in the creative process.
- Moratorium on Job Replacement: Propose a moratorium on the use of AI to replace writers' jobs entirely until the long-term implications and impacts are better understood.
[Additional proposals included: Training and collaboration, re-skilling and support, and clear rights to intellectual property.]
These are just some potential suggestions. The actual outcome would depend on the specific circumstances, the demands of both parties, and the willingness to find common ground between the WGA and the AMPTP.
It’s possible that ChatGPT might be biased. So, I asked my friend, Google Bard, the same question. His*5 response was:
Here are some guardrails that the Writers Guild of America negotiators could suggest to the AMPTP:
- AI should not be used to replace writers. AI should be used to augment the work of writers. AI should be used to help writers with tasks such as research, brainstorming, and editing, but it should not be used to create entire scripts or stories without human input.
- Writers should have control over the use of AI in their work. Writers should have the right to decide whether or not to use AI in their work, and they should have the right to review and approve any AI-generated content before it is used in their projects.
- AI should not be used to discriminate against writers. AI should not be used to make decisions about writers based on their race, gender, age, or any other protected characteristic.
- AI should be used in a transparent and accountable way. Writers should be able to understand how AI is being used in their work, and they should be able to hold producers and studios accountable for any misuse of AI.
These are just a few suggestions. The AMPTP may or may not agree to all of these suggestions, but it is important for writers to advocate for their interests in this area.
This was a lot less detailed than the response Myers got from ChatGPT. So, I asked some clarifying questions in follow up.
What do you think about human oversight of the work done by AI?
Response:
I think it is essential to ensuring that AI is used in a safe, ethical, and responsible way. AI systems are complex and can make mistakes, so it is important to have humans in the loop to monitor their performance and intervene when necessary. Human oversight can help to prevent AI systems from making discriminatory or unfair decisions, and it can also help to ensure that AI systems are aligned with human values.
Here are some specific examples of how human oversight can be used to improve the safety and ethics of AI:
- In the healthcare industry, human oversight can be used to review the output of AI systems that are used to diagnose diseases or recommend treatments.
- In the financial industry, human oversight can be used to review the output of AI systems that are used to make investment decisions.
- In the criminal justice system, human oversight can be used to review the output of AI systems that are used to make bail decisions or sentencing recommendations.
As AI systems become more sophisticated, it will become increasingly important to have human oversight in place to ensure that they are used in a responsible way.
OK. That didn’t address the film industry, but this problem goes well beyond the entertainment field.
I next asked about fair compensation, following up on an area suggested by ChatGPT. You can see that in the full text at the end of this story.
But, let’s cut to the chase:
The AMPTP has much more economic power than the WGA. Many of its members are powerful international companies, like Disney and Netflix. The primary economic power for the WGA comes from its ability to strike. But writers are already underpaid and most struggle to pay for rent and food. Other than a strike, what kind of power should the WGA use to get fair compensation from AMPTP companies?
Bard’s response:
The WGA is in a difficult position when it comes to negotiating with the AMPTP. The AMPTP has much more economic power, and writers are already underpaid. This makes it difficult for the WGA to use its economic power to pressure the AMPTP into making concessions.
However, there are other ways for the WGA to get fair compensation from AMPTP companies. Here are a few suggestions:
- Use its political power: The WGA can use its political power to pressure the government to pass laws that would benefit writers. For example, the WGA could lobby for laws that would increase minimum wages for writers or that would provide more protections for writers' jobs.
- Use its cultural power: The WGA can use its cultural power to pressure the AMPTP. For example, the WGA could encourage writers to refuse to work on projects that are not produced by companies that are fair to writers. The WGA could also launch a public relations campaign to educate the public about the importance of fair compensation for writers.
- Use its collective power: The WGA can use its collective power to pressure the AMPTP. For example, the WGA could coordinate its efforts with other unions in the entertainment industry. This would make it more difficult for the AMPTP to ignore the demands of writers.
These are just a few suggestions for how the WGA can get fair compensation from AMPTP companies. It is important for the WGA to use all of its resources to fight for the rights of writers.
Here are some additional thoughts on how the WGA can use its power to get fair compensation from AMPTP companies:
- Be creative: The WGA needs to be creative in its approach to negotiations. The AMPTP is a powerful opponent, and the WGA needs to find new and innovative ways to pressure them.
- Be united: The WGA needs to be united in its demands. If the writers are divided, the AMPTP will be able to play them off against each other.
- Be patient: Negotiations can take time. The WGA needs to be patient and persistent in its efforts to get fair compensation.
Getting fair compensation from AMPTP companies is a long and difficult fight. However, the WGA is committed to fighting for the rights of writers, and it will not give up until writers are fairly compensated for their work.
Here is where I wrapped it up with Bard, thanking him for his ideas. In response, Bard noted:
I agree that massive displacement of writers, directors, and actors by artificial intelligence would be very disruptive to the economy and could lead to suffering and even death for humans. It is important to find a way to integrate artificial intelligence into society to the benefit of all.
By taking these steps, we can help to ensure that AI is used in a way that benefits all of humanity.
Ever the optimist, I see.
So, what can we take from this? I think Bard has a great point that we have to think beyond just negotiating with the AMPTP. Specifically, we need the government to set minimum standards for companies using artificial intelligence.
Congress should set its own MBA (minimum basic agreement) for the entertainment industry—and other industries.
This is personal. You need to think about this in terms of your own job or profession. What are you going to do when you are replaced by a button?
I’d like Congress to implement the following in law:
Regulate use of artificial intelligence on MBA-covered projects: AI can't write or rewrite literary material; can't be used as source material; and MBA-covered material can't be used to train AI.
Does that sound familiar to you? It should. This was the proposal the WGA made to the AMPTP. And there’s literally nothing wrong with it. It’s the basic minimum we need for the entertainment industry to continue to create great stories for the world. Actually, I think Congress should noodle on this and come up with a much better basic minimum, but they could start here.
Or, we could do nothing and let AI take over. There’s some sense to that. Why should humans have to work at all? Why not just let automation provide us with everything. We’d need to figure out how to provide enough income for humans to continue to buy things (or go to a non-market system). But presuming each human being could just get their needs fulfilled by automation, why not?
I can think of a couple reasons. One is that quality could suffer. Current critique of stories produced by AI is that they lack a certain, let’s say, human quality. But it would be naïve to think that today’s quality is indicative of future quality. Reports are that ChatGPT and other public systems are dumbed down, and that some of the experimental systems are far more creative.
Another potential pitfall is that humans might fail to prosper if they are coddled and don’t have to put any real thought into life. Kind of like the idle rich. A bit degenerate, possibly.
But, seriously, the biggest impediment is just this: No one would want this world. I wouldn’t mind having my creature comforts provided, but only so I can pursue the intellectual and emotional pursuits of life without spending too much time on drudgery. If I had to compete with AI thinking, I’m not sure I’d measure up. And even if I did, I could get lost in the chat. Heck, I get lost in the chat, as it is.
So, here’s my thought: This is a political problem. It isn’t just screenwriters and other creatives that are on the line, here. It’s us. It’s all of us. So, we, as humans need to demand legal protections for humans.
No, those shouldn’t shut down the AI industry (as if that were possible). We simply need to make sure there are the kinds of things ChatGPT and Bard suggested. Things like human oversight and fair distribution of intellectual property (IP).
We should not send out our screenwriters to do battle all alone with international corporations. We, the humans, need to band together and insist on suitable laws.
That’s the only way we can compete with these buttons.
Footnotes
*1 Trying not to give away my age, and failing.
*2 WGA means the “Writers Guild of America” and SAG-AFTRA means the “Screen Actors Guild - American Federation of Television and Radio Artists”. WGA has two sides: Writers Guild of America West and Writers Guild of America East.
*3 AMPTP means the “Alliance of Motion Picture and Television Producers”. It represents more than 350 American television and film production companies, including the largest. See their page on Wikipedia.
*4 Scott Myers, Associate Professor, DePaul University. He is a screenwriter and a member of WGA since 1987. Find him at GITSblog@gmail.com.
*5 I use the male pronouns he/his/him for Bard, but for all I know Bard is a female. Or, even some kind of neutral gender. For convenience, however, I’m going to use male for him, and you can think of him in other ways if you want.
Complete Text of AI Exchanges
Here is the complete text of the exchanges Scott Myers and I had with generative AI.
Scott Myers prompted ChatGPT for suggestions on how the WGA should negotiate with AMPTP:
The Writers Guild of America is currently on strike. On the other side is the AMPTP who represent streaming services like Netflix and the studios like Paramount and Disney. One of the big issues is the use of AI (Artificial Intelligence) as part of the process in developing and producing TV episodes and movies. Writers are concerned about AI's impact on how we do their jobs and potential loss of work due to reliance on AI. Are there any guardrails the Guild negotiators can suggest which the AMPTP will agree to?
ChatGPT responded:
As an AI language model, I don't have real-time information, and my knowledge is up to September 2021. However, I can suggest some potential guardrails that the Writers Guild of America (WGA) negotiators could propose concerning the use of AI in the creative process, with the aim of protecting the interests of writers while addressing the concerns of the AMPTP, which represents streaming services and studios:
- Human Oversight: Ensure that AI is used as a tool to assist writers rather than replace them. Propose a requirement for human oversight in all AI-assisted processes to maintain the creative input and vision of writers.
- Fair Compensation and Job Security: Negotiate for fair compensation and job security for writers in instances where AI is implemented. Writers could receive additional compensation for the use of their work in AI-generated content and provisions to protect against job losses due to over-reliance on AI.
- Creative Control: Establish clear guidelines that maintain the creative control of writers over their work when AI is involved. This could include safeguarding against significant alterations or unauthorized use of writers' content.
- Training and Collaboration: Encourage opportunities for writers to collaborate with AI technology experts and be involved in the training and development of AI tools. This way, writers can help shape AI tools to be more beneficial to their creative process.
- Transparency and Accountability: Demand transparency from studios and streaming services regarding the use of AI in the creative process. The WA could propose mechanisms to ensure accountability for how AI is used and how it may affect writers' work.
- Moratorium on Job Replacement: Propose a moratorium on the use of AI to replace writers' jobs entirely until the long-term implications and impacts are better understood. This could allow for a period of assessment and negotiation.
- Reskilling and Support: Advocate for programs that support writers in acquiring new skills or transitioning to other roles within the industry, in case AI implementation affects traditional writing opportunities.
- Intellectual Property Rights: Negotiate for clear intellectual property rights for writers when it comes to AI-generated content. Writers should retain ownership and receive appropriate compensation for their contributions to AI-generated works.
These are just some potential suggestions that could be put forward by the Writers Guild of America during negotiations. The actual outcome would depend on the specific circumstances, the demands of both parties, and the willingness to find common ground between the WA and the AMPTP.
I asked my friend, Google Bard, the same question. His response was:
Here are some guardrails that the Writers Guild of America negotiators could suggest to the AMPTP:
- AI should not be used to replace writers. AI should be used to augment the work of writers, not to replace them. This means that AI should be used to help writers with tasks such as research, brainstorming, and editing, but it should not be used to create entire scripts or stories without human input.
- Writers should have control over the use of AI in their work. Writers should have the right to decide whether or not to use AI in their work, and they should have the right to review and approve any AI-generated content before it is used in their projects.
- AI should not be used to discriminate against writers. AI should not be used to make decisions about writers based on their race, gender, age, or any other protected characteristic.
- AI should be used in a transparent and accountable way. Writers should be able to understand how AI is being used in their work, and they should be able to hold producers and studios accountable for any misuse of AI.
These are just a few suggestions for guardrails that could be put in place to protect writers from the potential negative impacts of AI. The AMPTP may or may not agree to all of these suggestions, but it is important for writers to advocate for their interests in this area.
I asked some clarifying questions in follow up.
What do you think about human oversight of the work done by AI?
Response:
I think human oversight of the work done by AI is essential to ensuring that AI is used in a safe, ethical, and responsible way. AI systems are complex and can make mistakes, so it is important to have humans in the loop to monitor their performance and intervene when necessary. Human oversight can help to prevent AI systems from making discriminatory or unfair decisions, and it can also help to ensure that AI systems are aligned with human values.
There are a number of ways to implement human oversight of AI. One approach is to have humans manually review the output of AI systems. This can be a time-consuming and labor-intensive process, but it can be effective in ensuring that AI systems are making accurate and fair decisions. Another approach is to use machine learning to train humans to spot potential errors in AI systems. This can be a more efficient way to implement human oversight, but it is important to ensure that the machine learning model is accurate and unbiased.
Ultimately, the best approach to human oversight of AI will depend on the specific application. However, I believe that human oversight is essential for ensuring the safe and ethical use of AI.
Here are some specific examples of how human oversight can be used to improve the safety and ethics of AI:
- In the healthcare industry, human oversight can be used to review the output of AI systems that are used to diagnose diseases or recommend treatments. This can help to prevent AI systems from making errors that could harm patients.
- In the financial industry, human oversight can be used to review the output of AI systems that are used to make investment decisions. This can help to prevent AI systems from making risky or unethical investments.
- In the criminal justice system, human oversight can be used to review the output of AI systems that are used to make bail decisions or sentencing recommendations. This can help to prevent AI systems from discriminating against certain groups of people.
These are just a few examples of how human oversight can be used to improve the safety and ethics of AI. As AI systems become more sophisticated, it will become increasingly important to have human oversight in place to ensure that they are used in a responsible way.
Another follow-up:
What about fair compensation and job security for writers? Is there a way to negotiate terms that would be fair to both writers and the AMPTP members?
Response:
Yes, there are a number of ways to negotiate terms that would be fair to both writers and the AMPTP members. Here are a few suggestions:
- Increased minimum wages and residuals: The WGA is currently seeking a 40% increase in minimum wages for writers, as well as increased residuals for writers' work on streaming platforms. This would help to ensure that writers are fairly compensated for their work, regardless of the medium in which it is produced.
- Improved job security: The WGA is also seeking improved job security for writers, such as guaranteed minimum work weeks and severance pay for writers who are laid off. This would help to ensure that writers have a more stable income and can plan for their future.
- Increased transparency: The WGA is also seeking increased transparency from the AMPTP about how they make decisions about compensation and job security. This would help writers to understand how their work is valued and to advocate for their interests more effectively.
These are just a few suggestions for how to negotiate terms that would be fair to both writers and the AMPTP members. It is important for both sides to be willing to compromise and to work together to find solutions that meet the needs of everyone involved.
Here are some additional thoughts on how to negotiate fair compensation and job security for writers:
- Consider the changing landscape of the entertainment industry: The entertainment industry is constantly evolving, and this has implications for the way that writers are compensated and employed. For example, the rise of streaming platforms has led to shorter seasons and lower residual payments for writers. The WGA needs to be mindful of these changes and to negotiate terms that reflect the realities of the current industry.
- Build relationships with AMPTP members: It is important for the WGA to build relationships with AMPTP members. This will help to create a more collaborative environment and make it more likely that both sides will be willing to compromise.
- Be prepared to strike: If negotiations fail, the WGA may need to be prepared to strike. A strike is a powerful tool that can be used to pressure the AMPTP to make concessions. However, it is important to use this tool wisely and to make sure that it is in the best interests of writers.
Negotiating fair compensation and job security for writers is a complex and challenging task. However, it is an important one, and the WGA is committed to fighting for the rights of writers.
The big question is:
The AMPTP has much more economic power than the WGA. Many of its members are powerful international companies, like Disney and Netflix. The primary economic power for the WGA comes from its ability to strike. But writers are already underpaid and most struggle to pay for rent and food. Other than a strike, what kind of power should the WGA use to get fair compensation from AMPTP companies?
Response:
The WGA is in a difficult position when it comes to negotiating with the AMPTP. The AMPTP has much more economic power, and writers are already underpaid. This makes it difficult for the WGA to use its economic power to pressure the AMPTP into making concessions.
However, there are other ways for the WGA to get fair compensation from AMPTP companies. Here are a few suggestions:
- Use its political power: The WGA can use its political power to pressure the government to pass laws that would benefit writers. For example, the WGA could lobby for laws that would increase minimum wages for writers or that would provide more protections for writers' jobs.
- Use its cultural power: The WGA can use its cultural power to pressure the AMPTP. For example, the WGA could encourage writers to refuse to work on projects that are not produced by companies that are fair to writers. The WGA could also launch a public relations campaign to educate the public about the importance of fair compensation for writers.
- Use its collective power: The WGA can use its collective power to pressure the AMPTP. For example, the WGA could coordinate its efforts with other unions in the entertainment industry. This would make it more difficult for the AMPTP to ignore the demands of writers.
These are just a few suggestions for how the WGA can get fair compensation from AMPTP companies. It is important for the WGA to use all of its resources to fight for the rights of writers.
Here are some additional thoughts on how the WGA can use its power to get fair compensation from AMPTP companies:
- Be creative: The WGA needs to be creative in its approach to negotiations. The AMPTP is a powerful opponent, and the WGA needs to find new and innovative ways to pressure them.
- Be united: The WGA needs to be united in its demands. If the writers are divided, the AMPTP will be able to play them off against each other.
- Be patient: Negotiations can take time. The WGA needs to be patient and persistent in its efforts to get fair compensation.
Getting fair compensation from AMPTP companies is a long and difficult fight. However, the WGA is committed to fighting for the rights of writers, and it will not give up until writers are fairly compensated for their work.
Wrapping up…
Thank you, Bard, for your advice on this matter. Massive displacement of writers, directors, and actors by artificial intelligence would be very disruptive to the economy and could lead to suffering and even death for humans. Finding a way to integrate artificial intelligence into society to the benefit of all would avoid many problems.
Response:
You're welcome. I'm glad I could be of assistance.
I agree that massive displacement of writers, directors, and actors by artificial intelligence would be very disruptive to the economy and could lead to suffering and even death for humans. It is important to find a way to integrate artificial intelligence into society to the benefit of all.
Here are a few things that we can do to ensure that AI is used in a safe, ethical, and responsible way:
- Educate the public about AI: It is important for people to understand how AI works and what its potential benefits and risks are. This will help to ensure that AI is used in a way that is beneficial to society as a whole.
- Develop ethical guidelines for AI: There need to be clear ethical guidelines for the development and use of AI. These guidelines should ensure that AI is used in a way that respects human rights and values.
- Create international agreements on AI: AI is a global technology, so it is important to have international agreements on how it is developed and used. These agreements should help to ensure that AI is used in a way that benefits all of humanity.
- Invest in AI research: We need to continue to invest in AI research so that we can develop safe and ethical AI systems. This research should be conducted in a transparent and accountable way.
By taking these steps, we can help to ensure that AI is used in a way that benefits all of humanity.