Posts

It has been one year since I started using chatGPT as my digital assistant. If I had my brain scanned under an MRI, between last year and now, there would sure be significant changes in the activity pattern. I don’t just use one tool but I use copilot for work, dall-e for images and chatgpt for everything else. So, what are the most significant changes I have noticed? My hesitancy to start a seemingly difficult task has reduced. Earlier, I would procrastinate on tasks that seemed difficult. Now, I just start the task and let chatgpt help me with it. I have noticed that chatgpt is able to help me with most of the tasks I throw at it. It is not perfect but it is good enough to get me started. Once I start, I am able to figure out the rest of the task on my own. I have become more organized and systematic. Travel plans, shopping lists etc can be created in a matter of seconds. I don’t work hard on the tasks that I don’t enjoy. I just ask chatgpt to do it for me. I have noticed that chatgpt is able to do most of the tasks that I don’t enjoy. I am able to focus on the tasks that I enjoy. I used to google and go on a search journey. Now, I ask chatgpt to do that. When in doubt, I ask it to give a good link to the sources so that I can do my own research. I am becoming less and less surprised by new technology. The sense of awe is fading away. With tools like copilot, I am always trying to look away from the suggestions it is providing if I want to use my creativity. This feels so weird when you know that the AI is already doing a good job but you still want to do it on your own. Each of those has its merits and issues. Some of the questions I often ask myself: ...

Last month, I started to build a personal finance app using OpenAI’s ChatGPT. Over the course of 30 hours, I saw my app idea come to life, all thanks to the power of AI. In this post, I’ll share my experience and the lessons I learned while working with ChatGPT. The code can be found here: https://github.com/ashwin67/finhandle ChatGPT as a personal assistant The process was incredibly smooth - I’d provide ChatGPT with a requirement, and it would generate Python, JavaScript, or HTML code snippets based on my request. It even remembered my directory structure and guided me on where to insert the new code. It felt like having a personal assistant that understood my project and could respond to my needs. ...

Can you believe that none of the following including the image was written by me! All I did was to ask chatGPT to write a conversation between a software engineer and a photographer about AI technologies and conclude about the future. I provided a similar prompt to Dall-e Software engineer: Hey photographer, have you heard about the new AI technologies that are coming out? Photographer: Yeah, I’ve heard a bit about them. What’s got you so excited? ...

Let’s say you do not know how to program in Rust but you do know programming itself. You will need to install rust, create a project etc. After that, you can just start programming in Rust. While I am writing some things, most of the code is actually written by Github copilot. I just need to tell github copilot what to do and it just does the job for me. This makes it really easy to learn a new language. Typically, my workflow when encountering an unknown during coding is as follows: ...

Let us say, we are looking out of a beach under clear blue skies towards a few ships sailing away. How did we know that we were looking at the sea, above was the blue sky and those were ships. Isn’t it quite amusing that we have a name for everything that we want to name? And that we have learnt how to differentiate between those names? Would a 3 month old child know how to differentiate between the sky and the sea, considering that both are blue? Or would it know but would just lack the capability to express the difference in terms of names? A 3 year old child would probably have seen ships in books and TV and as a result, when it sees a real ship on a sea, it would immediately make a best guess that it is a ship; Anything so big and floating on sea should be a ship. Basically, the child is finding a pattern. Repeated pattern finding and confirmation (in this case, a verification by the child’s parent) would enforce the idea that it is a ship. Errors can still be possible. Even a grown up person can see an oil rig in the middle of the ocean from far and mistake it to be some ship (since the pattern matching algorithm would first point to a ship). ...