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.
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?
Looks like self realization is one of those blocked keywords.
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)
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:
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.
Subscribe to:
Posts (Atom)