ashraful

Its almost always through personal connections or word of mouth/referrals.

The primary concern for small to medium business is if the consultant being hired is actually capable of providing the service they are claiming to provide.

Hiring someone off of an online ad, cold call, etc. is just unnecessary risk. They'd happily pay more when they know that the output is going to be what they expect.

> results can be as fast as 10x the audio length

shouldn't this say 1/10th instead?

"Fair play" in mystery novels means the author gives you all the clues up front, so you have a shot at solving the mystery just like the book's detective.

Events are considered high risk by payment processors because the nature of events is that you sell the tickets before the event (ie. you accept payment without providing the service).

Shopify focuses more on people selling physical goods (traditional ecommerce), so maybe consider a platform that caters specifically to events/services - maybe something like woocommerce?.

You can use some clever prompts to see this summarization in action.

I had a long conversation with chatgpt, asking it about a book, and provide plot summaries, and asking about specific characters. After about 40-50 questions, I asked it questions like how many questions I have asked in this conversation and what they were. Eventually I was able to get it to print out the questions I asked, and they all got shortened (a lot!).

From what I understand (this might be an oversimplification).

Each prompt-response is independent, and it doesn't have a real understanding of the historical context of the conversation. This means that when you talk to the chatbot, the entire conversation history needs to be included in the prompt to give it context.

For instance, if your first prompt is "Who is the current sitting president of the United States?" and the response is "Joe Biden," and you then ask a follow-up prompt like "How tall is he?", GPT-3 won't understand what you're referring to unless the prior conversation is included in the prompt, like so:

```

User: Who is the current sitting president of the United States?

AI: Joe Biden

User: How tall is he?

AI:

```

By doing this, GPT-3 can use the context of the previous conversation to generate an appropriate response. However, as the conversation history gets longer, GPT-3's ability to maintain context weakens, and it may begin to provide irrelevant or nonsensical responses.

There is a soft limit of around 2000 tokens, which translates to approximately 1500 words. When the conversation history becomes too long, GPT-3 will summarize it in a way that preserves the important information. For example, "Who is the current sitting president of the United States?" might become "Who's the president of USA" to save space.

For most users, including the entire conversation history in the prompt is feasible for up to six prompts before context begins to degrade. After that point, it may be necessary to restate previous information or use other methods to maintain context.

While I believe that ChatGPT and Bing likely have more advanced methods for retaining conversation history, based on the recent limitations implemented, it seems that the general principle of maintaining context still holds true.

Can you let me know what part is not working for you? Does the entire site not load?

To play a song, double-click on it, or click once and then click on the play button. Let me know if that doesnt work.