llm posts
- A view of 2026 from 1927 4 minutes
Metropolis, a 1927 sci-fi movie, is set in a dystopian capitalist society where a whole city is owned by Joh Frederson. The story revolves around his son, Freder Frederson, wandering around the city having an adventure. To put it simply. It’s about class struggle. Maybe faith. At one point, I thought it’s an anti-capitalist movie and at another point, I thought it’s anti-communist… but maybe it’s both or neither.. it’s just a movie.
I started it out of curiousity to get a perspective on what people thought of as super futuristic in 1927. The movie is said to be set in 2026. The year I’m currently writing this in. It’s 18th January, 2026. It feels a little surreal that people 100 years ago dreamed of this time and made stories about it. I’ll go over the technology of Metropolis (as much as I could understand it) in this blog article.
- Lessons from LLMs and Life 9 minutes
“The unpredictability in life is what makes it interesting”
I’m Mahesh Bansod. A software engineer. I love building stuff for the sake of building it.
Building software has never been so simple - type a prompt and boom you got a working interactive system!
I really love this era. I have been programming since years now, and I still love to. I find the most joy in building software when I’m programming it as opposed to when I’m prompting it, but it’s wonderful to see applications come to life as I type in English what I want!
There’s one thing I struggled with though while working with an LLM and that is deterministic output.
If you do the same prompt a second time, it is sure to give you a totally different output.. and maybe the second time it may not even work when the first time it did!
This “non-deterministic”ness of it all has been making me draw parallels to life.
- Making LLMs do what you want 12 minutes
Tired of spending hours convincing an LLM to just do that one thing? You have tried lots of different ways to no satisfaction and yet it eludes you why it isn’t able to just do this really simple task? Look no further! You’ve reached the place you’ll learn the dark arts of making any LLM head over heels for you. I have worked with LLMs since about two years now and this guide is about what I learnt and how we can ensure the best prompts while also modifying prompts to accomodate evolving requirements.
"It's like all my life everybody keeps telling that I'm a shoe. You're a shoe, you're a shoe, you're a shoe! But what if I don't want to be a shoe anymore? Maybe I'm a purse, or a hat..."
— Rachel Green