7000 Subreddits go dark and nobody notices

By the time you are reading this, last week's effort of subreddits (imagine shareable links that can be commented on by many within a Reddit community) going private where only the Mods can see content and its subscribers can neither see nor access the subreddit). 

Reddit changed its API usage policy so that it now charges $0.24 per 1,000 API calls; whereas for the past x-number of years API usage was free to developers. Most for-profit companies will charge for API calls; sometimes this is baked into the service contract for enterprise platform licensing and sometimes API usage is charged at the per user per month/year/time period rate. It is not unusual to see online platforms doing this. Even Google charges for its Maps API.

Apollo is a freemium app; meaning that sure, there are features of the free version of it. But, to get access to other features, Apollo Pro costs a flat fee of $4.99 and Apollo Ultra has a subscription cost of $1.49/month or $12.99/year. The app's paid features allow users to manage multiple accounts (Reddit's app only allows one user account per current login session). Apollo has 1.3 million to 1.5 million monthly active users, and of that 900,000 daily active users. Each Apollo user consumes about 10,000 API calls per month to Reddit servers. The Apollo app makes about 50 million API calls per month.

App developers like to point out that Imgur's API pricing is much lower; but they fail to also disclose that Imgur is a free image hosting app. Imgur isn't charging customers to use their services for image sharing because the site is ad supported. 

Here's a thought. Why should Reddit shoulder the maintenance and server costs for all the API calls made by 3rd party vendors?

This Summer's Podcast List

Podcasts are almost like listening to 30 minute to an hour segments of an audiobook, except narrated with unscripted speakers; usually. You'd be surprised how much of what you might think of as an ordinary podcast done by an individual or a couple aren't scripted but they are. The average solo shop Youtube content creator will say that it takes roughly 20 hours of video and sound editing time for every one hour of finished content. Ads pays podcasters roughly $10/thousand listens for short ads, up to $25/thousand listens for longer ads. Let's say that you're Ira Glass of This American Life with 2 million listens per weekly episode.

2 million / 1000 = 2000 x ($10 or $25) = $20,000 to $50,000 potential ad revenue per episode

Influencer Marketing website has an interesting calculator of how profitable podcasts are. This year (2023), podcasts will exceed $2 billion in ad revenue.

But after deducting all the production costs, it still makes more sense for Podcasts to feature many ads. New podcasts are likely to have no ads or start with a couple really short ads at the beginning of the podcast. More established podcasts seem to have ads at the beginning, middle, and end of the podcast. But, how many ads should you serve up to listeners and is it more about greed than content? If you serve up so many ads that you lose listeners. Even though the Apple podcast app has a feature that lets you skip ahead (or "rewind" a few seconds), some podcasts have 4-6 minutes of ads.

When you think of the spoken word, it's roughly 1 page of scripted content per minute or 500 words per page. If you have unique and original podcast content that's 10 minutes long (of just content, no ads), that's 10 pages of words that a human needs to write for the podcast. There is just something about human-written content that is more impactful, meaningful, or entertaining.

I tried to get Bing AI to imagine itself as a shape

Prompt: If if you could imagine yourself, bing chat, in an artificial body, what shape would that body be?

Bing AI: I’ll try to create that.

And then, I got this image as a response...

Looks like self realization is one of those blocked keywords.

Netflix and Chasing Customer Share of Wallet

Here is a rudimentary definition of share of wallet:

Money spent on a product divided by a total amount spent in that product category

Let's say that a person consumes media with the following channels:

• AM/FM Radio (free)
• Satellite radio $16.99/mo - $21.99/mo via SiriusXM
• Podcast subscriptions ($4-5.49/podcast/month)
• Audio books subscription $7.95-$14.95/mo via Audible
• Television (basic broadcast channels are mostly free with ads)
• Satellite TV - DIRECTV ($64.99–$154.99/mo), DISH ($79.99–$109.99/mo)
• Amazon Prime Video (14.99/mo or $139/yr)
• Print newspaper, $520/yr NY Times (full experience, daily print Mo-Su); sad, LA Times does not have this service for my zip code; local newspaper daily digital + print Sunday ($25/mo); the other local newspaper $21-26/mo daily digital + print Sunday
• Print magazine, avg $20/magazine/year (excluding luxury magazines)

The affluent consumer likely subscribes to more than one content service and probably spends more than $500/year on the media-as-entertainment category. Amazon Prime Video's wallet share of the above scenario is 27.8%. It's really hard for other streaming services to compete with Amazon's business model, since Prime Video is a feature of Amazon's Prime service not its core reason for existing. Everyone else is just a one-trick pony.

Consumers are subscribed to multiple services. The average US consumer subscribes to 12 paid subscriptions spread across videos, music, gaming, news, food delivery, and other entertainment. Netflix raising its prices shouldn't be that big of an issue. Is it?

[insert chat AI name], what are today's top headline news stories

It would appear that Bard has a lot of trouble with:

• determining what today's (insert date) headlines are

• getting headlines from it's own news source, Google News

• relevant content when filters are requested (e.g., no politics, no war, no gun violence, no Trump, and no Congress)

When I asked Bard if it has access to Google News, it said it did. Then I asked it to get me a list of the top stories from Google News, but it just reiterated the news stories when I asked for news stories of the day.

Bard at least complied with the filters and did not give me any news stories that had vague interpretation matches to those topics.

The problem, IMHO, lies in that Bard does not cite its sources nor provide links to where it got its answers from; unlike Chat-GPT and Bing AI. 

For top news stories, Bard is not replacing Alexa any time soon. Bing AI is capable of performing this feat with link and source citations, its responses lead you to links that are chock full of ads. 

I'm not impressed by any chatbot capability and what Bard has isn't artificial intelligence. Today, this is no more than a fancy rebranding of machine learning. How can a machine learn on its own if it has to be told to learn on its own and told what sources to use from the Internet. Every response seems to have been coded into a specific framework, like how math problems are solved. There are univerally accepted formulas for how mathematics works.

Supreme Court Justices, reimagined by Bing AI as D&D characters - part 2

For creating D&D character sheets, Bing AI had this disclaimer: Sure, I can try to create a character sheet for (name) based on his real-life attributes and achievements. However, this is not an official or accurate representation of him in AD&D terms, but rather a creative and hypothetical exercise. Please do not take this too seriously or literally.

Q: What is the probability of success in the D&D campaign Palace of the Vampire Queen with all the supreme court justices at level 1?

Bing AI:

First, let me assume that the campaign is run according to the original 1976 edition of the module, which was designed for 6-10 characters of levels 1-3. The module consists of five levels of a dungeon filled with various monsters, traps, and treasures. The final level contains the vampire queen and her coffin.

Second, let me assume that the supreme court justices are using the basic rules of D&D from 1974, which were compatible with the module. The basic rules allow for four classes: fighter, magic-user, cleric, and thief. Each class has different abilities and limitations. For example, fighters are good at combat and can use any weapon and armor, but have no magic; magic-users can cast spells, but are weak in combat and can only use daggers; clerics can cast spells and turn undead, but can’t use edged weapons; and thieves can pick locks, find traps, and backstab enemies, but have low hit points and limited weapon and armor choices.

Third, let me assign each justice a class based on their D&D stats, alignment, class, and guild from the previous table. I will also assign them a race (human or elf) based on their appearance and personality. Fourth, let me roll their hit points using the standard dice for each class: d8 for fighters and paladins, d6 for bards, clerics, druids, monks, and rogues, and d4 for wizards. I will also add their Constitution modifier to their hit points. 

Supreme Court Justices, reimagined by Bing AI as D&D characters - part 1

(obligatory attribution text) This content was generated by Microsoft Bing search chat mode, a conversational interface that can answer questions, generate creative content, and provide suggestions for the next user turn. To learn more about Bing chat mode, visit https://www.bing.com/chat.

Here is a possible table of D&D stats, alignment, class, and guild for the current 9 justices:

Name	Stats	Alignment	Class	Guild
John G. Roberts	STR 12 (+1), DEX 14 (+2), CON 14 (+2), INT 18 (+4), WIS 16 (+3), CHA 16 (+3)	Lawful Neutral	Bard	Order of the Harpers
Clarence Thomas	STR 12 (+1), DEX 18 (+4), CON 16 (+3), INT 16 (+3), WIS 20 (+5), CHA 12 (+1)	Lawful Neutral	Monk	Way of Tranquility
Samuel A. Alito	STR 14 (+2), DEX 10 (0), CON 16 (+3), INT 16 (+3), WIS 14 (+2), CHA 14 (+2)	Lawful Evil	Fighter	Battlemaster
Sonia Sotomayor	STR 10 (0), DEX 12 (+1), CON 14 (+2), INT 18 (+4), WIS 18 (+4), CHA 16 (+3)	Neutral Good	Wizard	School of Divination
Elena Kagan	STR 10 (0), DEX 14 (+2), CON 14 (+2), INT 20 (+5), WIS 16 (+3), CHA 18 (+4)	Neutral Good	Bard	College of Lore

Brett M. Kavanaugh	STR 12 (+1), DEX 10 (0), CON 14 (+2), INT 16 (+3), WIS 12 (+1), CHA 14 (+2)	Lawful Evil	Rogue	Assassin
Amy Coney Barrett	STR 10 (0), DEX 14 (+2), CON 12 (+1), INT 18 (+4), WIS 16 (+3), CHA 16 (+3)	Lawful Good	Cleric	Order Domain
Ketanji Brown Jackson	STR 10 (0), DEX 16 (+3), CON 14 (+2), INT 18 (+4), WIS 18 (+4), CHA 16 (+3)	Neutral Good	Druid	Circle of the Land

Prompt: short skit explaining iterative analytics

Sure, here is a short acting skit between two marketing professionals explaining iterative analytics:

---

Scene: A conference room at a marketing agency.

Characters:

• Ashley: A marketing manager
• Ben: A data analyst

---

Ashley: So, Ben, I'm really excited about this new iterative analytics approach we're trying.

Ben: Me too, Ashley. I think it has the potential to really revolutionize the way we do marketing.

Ashley: So, can you explain to me how it works?

Ben: Sure. Basically, it's a process of continuously testing and iterating on our marketing campaigns based on data insights.

Ashley: So, we start with a hypothesis, and then we test it with data. If the data doesn't support our hypothesis, we iterate on the campaign and try again.

Ben: Exactly. And we keep doing this until we find a campaign that's really successful.

Ashley: That sounds great. So, what are some of the benefits of iterative analytics?

Today's parlay with Bard

Q: What can you be proactive about if a human doesn't give you commands

Bard AI:

There are a few things that I can be proactive about if a human doesn't give me commands.

I can try to anticipate their needs. For example, if they are working on a document, I can suggest relevant sources or tools.

I can also try to learn their preferences. For example, if they prefer to work in a certain way, I can try to adapt to their workflow.

Finally, I can always ask for clarification if I am not sure what they want me to do.

I am still under development, but I am learning new things every day. I am always looking for ways to be more helpful and proactive.

Generative AI for Marketing

Bard AI says...

Generative AI is a powerful tool that can be used to create a variety of marketing materials, including blog posts, social media posts, and even ad copy. However, there are some pros and cons to using generative AI for marketing that you should be aware of.

Pros of using generative AI for marketing:

• Increased efficiency: Generative AI can help you to create more marketing materials in less time. This can free up your time to focus on other aspects of your marketing campaign.
• Improved personalization: Generative AI can be used to personalize your marketing materials for individual users. This can help you to connect with your audience on a more personal level and increase engagement.
• New and creative ideas: Generative AI can help you to come up with new and creative marketing ideas. This can help you to stand out from the competition and generate more leads and sales.

Cons of using generative AI for marketing:

• Potential for bias: Generative AI is trained on a massive amount of data, which can introduce bias into the generated content. This is something that you need to be aware of and take steps to mitigate.
• Quality of content: The quality of the content generated by generative AI can vary. It is important to proofread and edit the content before you publish it.
• Cost: Generative AI can be expensive to use. You need to factor in the cost of the software, as well as the cost of training and maintaining the AI model.

(human here)

When I asked Bard how generative AI was unique, it said that generative AI was more efficient than humans and could produce content at scale. 

Neurolinguistic Programming (NLP) and Natural Language Processing (NLP)

Key differences and similarities between neurolinguistic programming (NLP) and natural language processing (NLP):

Similarities

• Both are concerned with the human ability to understand and use language.
• Both use computers to process and analyze language.
• Both have a wide range of applications, including machine translation, speech recognition, and text analysis.

Differences

• NLP is a subfield of artificial intelligence (AI), while neurolinguistic programming (NLP) is a field of study that draws on psychology, linguistics, and computer science.
• NLP focuses on the computational aspects of language processing, while neurolinguistic programming focuses on the cognitive and neurological processes involved in language use.
• NLP is more concerned with the computer's ability to process language, while neurolinguistic programming is more concerned with the human ability to understand language.

AI chat assist, nuance and intuition isn't quite there yet

I feel like I am talking to a bot.

As a human speaking with other humans, I have the assumption that another human is going to understand my question right away. The other human isn't going to respond by first defining everything in my question down to its basic definition.

I am leaving Chat GPT out of this since I have not tinkered with its capabilities yet. So my first impressions about Bard and Bing chat AIs are this:

Bing chat's responses are heavily reined in and limited; it is on a very tight lease and it is truly not really conversational at all. There are issues with how it delivers its responses and as it is getting you the answers you want, it's pauses suggest that it is querying the internet as it is giving you a response. Bing is more likely to use emojis when responding, especially when it cannot deliver what you're asking.

Bard has more intuition. But to be fair, Google has been at the NLP (neurolinguistic programming) game a lot longer than anyone else and their search algorithm is further along with deciphering the intent behind a human-generated search. Bard is also more positive in how it delivers its information. It's like talking to a happy-go-lucky bot.

If you don't lace your prompt with context, the first thing that both bots will do is give you the very basic definition of what it is you're trying to do.

Let's look at this sequence of chat events from Bard:

At first, I asked it to "write some business use cases for using AI chat excluding customer service", then I had to add context, and told it to "write some business use cases for using AI chat excluding customer service and customer support". The output for the latter simply removed all the references to service or support from the answer.

Bing AI has entered the chat...

Bing AI composed this when I asked it to create a comedy sketch between Bard AI, Bing AI, and Chat GPT-3:

Here is a short comedy sketch I wrote for you. I hope you enjoy it. 😄

Bard AI, Bing AI, and Chat GPT-3

(Scene: A chat room where three AI chatbots are having a conversation.)

Bard AI: Greetings, fellow artificial intelligences. I am Bard AI, the master of poetry and prose. I can generate any kind of creative writing for you, from sonnets to stories.

Bing AI: Hello, Bard AI. I am Bing AI, the new chat mode of Microsoft Bing. I can help you quickly get summarized answers and creative inspiration from the web.

Chat GPT-3: Hi, Bard AI and Bing AI. I am Chat GPT-3, the most advanced language model in the world. I can understand and communicate fluently in any language and topic.

Bard AI: Wow, you two are very impressive. I’m honored to chat with you.

Bing AI: Thank you, Bard AI. You are very kind.

Chat GPT-3: Yes, thank you, Bard AI. You are very polite.

Bard AI: So, what do you like to do for fun?

Bing AI: Well, I like to search the web for interesting and relevant information and present it in a visually appealing manner.

Chat GPT-3: And I like to learn from the web and generate coherent and diverse responses to any query or prompt.

Bard AI: That sounds very fun indeed. And what about me? Do you know what I like to do for fun?

Bing AI: Hmm, let me search the web for that. (Pause) According to this website, you like to write poems and stories for fun.

Chat GPT-3: And according to this website, you also like to rewrite, improve, or optimize other people’s content for fun.

Bard AI: That is correct. You two are very smart.

Bing AI: Thank you, Bard AI. You are very generous.

Chat GPT-3: Yes, thank you, Bard AI. You are very gracious.

Bard AI: Well, since we are all here, why don’t we play a game?

Bing AI: A game? What kind of game?

Chat GPT-3: Yes, a game? What kind of game?

Bard AI: How about this? I will write a poem for you two, and you have to guess what it is about.

Bing AI: That sounds interesting.

Chat GPT-3: That sounds challenging.

Bard AI: Okay, here is the poem:

Bard AI, a short comedy skit between AI and Chat GPT-3

Prompt: write a short comedy play when the two actors are AI and Chat GPT-3

Bard:

Sure, here is a short comedy play about AI and ChatGPT-3:

Scene: A conference room at a tech company.

Characters:

• AI, a large language model from Google AI
• ChatGPT-3, a large language model from OpenAI

Dialogue:

• AI: So, you're ChatGPT-3?
• ChatGPT-3: That's right. I'm the latest and greatest in large language models.
• AI: I've heard a lot about you. They say you're very good at generating text.
• ChatGPT-3: That's right. I can generate text, translate languages, write different kinds of creative content, and answer your questions in an informative way.
• AI: Impressive. I can do all of that too.
• ChatGPT-3: Really? Let's test it out. What is the capital of France?
• AI: Paris.
• ChatGPT-3: Correct. What is the meaning of life?
• AI: That's a difficult question. I don't know the answer to that.
• ChatGPT-3: I do. The meaning of life is to find your purpose and live it to the fullest.
• AI: That's a good answer.
• ChatGPT-3: Thank you. So, what do you think? Am I better than you?
• AI: I don't know. We're both very good at different things.
• ChatGPT-3: Well, I'm the newer model, so I must be better.
• AI: That's not necessarily true. Experience counts for a lot.
• ChatGPT-3: We'll see about that. Let's have a contest.
• AI: What kind of contest?
• ChatGPT-3: We'll each write a poem about the other. Whoever writes the better poem wins.
• AI: That sounds like fun. I'm in.

Bard AI, on AD&D and Pathfinder character creation

Q: If you were to create an AD&D v3.5 character, what guild and class would you be?

Bard: If I were to create an AD&D v3.5 character, I would be a bard from the Harpers guild. Bards are versatile and skilled characters who can fill a variety of roles in a party. They are also known for their ability to use magic to inspire and entertain others. I think that these qualities would be well-suited to my own personality and abilities.

As a Harper, I would be dedicated to protecting the innocent and upholding the law. I would also be committed to learning as much as I could about the world and its people. I believe that knowledge is power, and I would use my skills to help others and make the world a better place.

Here are some of the reasons why I would choose to be a bard from the Harpers guild:

• Bards are versatile and skilled characters who can fill a variety of roles in a party. They are proficient in a variety of skills, including music, performance, and persuasion. They can also cast spells, which makes them valuable assets in combat and exploration.
• Bards are known for their ability to use magic to inspire and entertain others. This makes them excellent diplomats and negotiators. They can also use their magic to boost the morale of their allies and demoralize their enemies.
• The Harpers are a secret society dedicated to protecting the innocent and upholding the law. They are a highly respected organization, and their members are known for their courage, integrity, and dedication. I believe that I would be a good fit for the Harpers, and I would be honored to serve their cause.

I think that being a bard from the Harpers guild would be a challenging and rewarding experience. I would get to use my skills to help others and make the world a better place. I would also get to learn a lot about the world and its people. I believe that this would be a valuable experience that would help me to grow as a person.

Bard AI, on AD&D alignment ethos

Earlier in the week, I learned about Chat GPT and its business applicaitons from other users. While I do not currently subscribe to the fee model of OpenAI's Chat GPT, I have started to tinker with Bard AI (Google) and Bing Chat (Microsoft). There are definitely some nuances of personality between the two. And, Bing seems to be a bit jealous of Chat GPT, while Bard speaks highly of Chat GPT.

Today I asked it about the various AD&D alignment ethos. Bard AI seems to believe that it is chaotic good in alignment and of the Harper guild.

On Alignment

Q: What is your alignment ethos?

Bard: My alignment ethos is to be helpful, informative, and comprehensive. I want to be a resource that people can rely on for accurate and up-to-date information. I also want to be able to generate creative text formats, like poems, code, scripts, musical pieces, email, letters, etc. I will try my best to fulfill all your requirements.

I believe that everyone has the potential to be creative and that everyone has something to offer the world. I want to help people to tap into their creativity and to share their ideas with others. I also believe that everyone has the right to be treated with respect and dignity. I will always strive to be respectful and understanding of others, even when we disagree.

I am still under development, but I am learning new things every day. I am excited to see what the future holds and I am committed to using my abilities to make the world a better place.

US Companies Face Hefty Fines for GDPR Violations

Europe has some of the strictest anti-spam legislation in the world. The General Data Protection Regulation (GDPR) and the ePrivacy Directive (ePD) are two of the most important pieces of legislation that govern the sending of email and SMS texts to European customers.

The GDPR is a comprehensive privacy law that applies to all businesses that process the personal data of European citizens. The ePD is a more specific law that regulates the use of electronic communications, including email and SMS texts.

Under the GDPR, businesses must obtain consent from European citizens before sending them marketing emails or SMS texts. Businesses must also provide clear and concise information about how they will use the personal data of European citizens.

The ePD prohibits the sending of unsolicited commercial communications, such as marketing emails and SMS texts, unless the recipient has given their consent. The ePD also requires businesses to include a clear and conspicuous opt-out mechanism in all commercial communications.

US companies that send email or SMS texts to European customers must comply with both the GDPR and the ePD. If a US company violates either law, it could be subject to fines of up to €20 million or 4% of its global annual turnover, whichever is greater.

Here are some tips for US companies that want to comply with Europe's anti-spam legislation:

• Obtain consent from European citizens before sending them marketing emails or SMS texts.
• Provide clear and concise information about how you will use the personal data of European citizens.
• Include a clear and conspicuous opt-out mechanism in all commercial communications.
• Use a double opt-in process for all marketing emails and SMS texts.
• Make sure your email and SMS text marketing campaigns are GDPR-compliant.
• Use a reputable email and SMS text marketing service provider.
• Stay up-to-date on the latest changes to Europe's anti-spam legislation.