ChatGPT for cavemen

-

I heard a lot about ChatGPT and thought to come out of my cave to find out what the hype is about. Is it going to eat all my lunch or eat me for lunch? 

Like any product I gave it all my details and signed up. I asked it about quantum computing an it gave some answer. So far so good. Next day I wanted to check its blogging skills. So I opened chatGPT and I got this .



I checked throughout the day and it is still down. So it won’t eat me till it is fed few more servers. 

Continuing after it was up. 

I asked it to write a blog about itself. Here is what was generated by chatGPT.

ChatGPT is a powerful language generation model developed by OpenAI. It is based on the GPT (Generative Pre-trained Transformer) architecture, which uses deep learning techniques to generate human-like text.

One of the key features of ChatGPT is its ability to understand and respond to natural language inputs. This makes it an ideal tool for a variety of applications, such as chatbots, language translation, and summarization.

Another important aspect of ChatGPT is its pre-training. The model is trained on a massive dataset of text, which allows it to understand the nuances and subtleties of human language. This pre-training also allows the model to generate more coherent and coherent text when compared to other language generation models.

In addition to its natural language understanding capabilities, ChatGPT also has the ability to generate text in a wide variety of styles and formats. This includes creative writing, news articles, and even code.

Overall, ChatGPT is a powerful and versatile language generation model that has the potential to revolutionize the way we interact with machines. Whether you're looking to build a chatbot or generate text for a website, ChatGPT is definitely worth exploring.


Then I asked to edit my blog post 5 Why. It did a decent job of editing. 


Then asked to about its licensing model. At this point chatGPT recommended talking to a human. Its creators do not trust it enough to discuss which is good fit for me.

Comments

Post a Comment

Popular posts from this blog

Greedy computing with API

-
Image
 We all know computing resources have a cost. Memory, long term storage, transportation and computing all have their own costs. There are lot of scenarios where your API end point won't be able to respond in time. These are scenarios where you need to use more resources to provide a response. Let us be greedy with our resources and explore different patterns which can solve this. Polling  This is a commonly used pattern where the caller initiates a process. Then keeps on checking if the process is complete. If the process is complete then the caller reads the data needed.  This is a good pattern when both systems are part of the same organization. At least developers of caller and callee should be able to discuss this implementation.  Call back This is an improvement over polling pattern. Here the caller supplies a call back URL to the long running process. Once the process is complete it calls the callback URL and informs the caller that process results are available now. 
Read more

Event driven architecture for micro services

-
This is a work in progress. I am designing an event driven architecture to be used in systems using micro services. Micro service architecture is popular because it solves few problems in development process. While it solves some problems it also brings in new problems to the table. Bad designs impact micro services harder than monoliths. But this is thought is for another time.  How micro services talk to each other. In a monolith you have one gigantic database, or you can easily call another component to process the information. In a microservice you can use a Que (or event bus) to pass the information. This is the problem I want to discuss. Main issue with que is it is not designed for this scenario. There are few products which give a good solution by providing a subscription-based approach. But these are large implementations. Using these is similar to bringing an excavator to plant a sapling in your garden. Yes, many people go with using these large implementations to resolve thi
Read more