Sarthak Sharma

Posted on Jan 7

How you used AI in 2024?

#ai #discuss #llm #watercooler

2024 seemed to be all about AI—everywhere you looked, it was AI this and AI that. But once we cut through the marketing hype, what was actually useful to you?

I'm curious to hear from the community:

What AI use cases did you integrate into your life in 2024?
Which products or tools did you find yourself relying on the most?
To make it more structured, let’s divide this into two broad categories:

Personal Life: Did AI help you with daily tasks, hobbies, or self-improvement?

Professional Life: Were there any tools or workflows that transformed how you work or made a significant impact on productivity?

Feel free to share both what worked and what didn’t for you, and everything in between. Let’s build a collective insight into how AI has shaped our lives this past year!

My Experience with AI in 2024:

Personal:

I used Arc Search by Arc Browser a lot as a replacement for Google Search when I wanted to find or learn something.
I used Ollama + Mixtral + Obsidian for journaling, marketing write-ups, and more. The Ollama Plugin enabled me to do AI-powered writing even offline.
I also used ChatGPT for various purposes, such as gardening, cooking, travel planning (along with Arc Search), interior design ideas, diet, and exercise planning.

Work:

ChatGPT is at the top of the list. While I used it less for handling complex bugs (I often resorted to forums and GitHub for those), it was very helpful for research and planning new projects.
Copilot has been great for improving programming speed. With new features and better models being released, I’m excited to explore them further. Overall, it’s an excellent autocomplete tool.
Ollama + Mixtral + Obsidian were also useful for work journaling.

I’m sure I’ve missed a lot, which is why I’m curious: How have you incorporated AI into your life in 2024?

Looking forward to hearing your experiences! 😊

Top comments (19)

Oscar • Jan 8

I almost never use AI, but the one of the two times I did this year was for converting a bunch of environment variables to docker compose variables, like so:

CSRF_COOKIE_SAMESITE="Strict"
SESSION_COOKIE_SAMESITE="Strict"
CSRF_COOKIE_HTTPONLY=False

- CSRF_COOKIE_SAMESITE=${CSRF_COOKIE_SAMESITE}
- SESSION_COOKIE_SAMESITE=${SESSION_COOKIE_SAMESITE}
- CSRF_COOKIE_HTTPONLY=${CSRF_COOKIE_HTTPONLY}

... plus about 30 more of these. Saved me about 15 minutes!

Sarthak Sharma • Jan 9

😂

Kevin Naidoo • Jan 10 • Edited

I've been using AI for nearly every aspect of my workflow and products:

Code generation, boilerplate stuff so I save time.
Voice AI: built a bunch of products using SIP and WebRTC.
Data processing. RAG, Product tagging, categorization, etc...
Finance. Scans my statements and generates different reports like balance sheets, income/expenditure reports, etc...
Chatbots, good old chatbots.
Documentation, when I do something in Java or some other language I haven't written in a while. Makes it easy to do a quick reference lookup.

Even amusement 😊 here's a recent voice AI implementation I shared on my blog.

Sarthak Sharma • Jan 10

Dope, you seem like a power users.

Which AIs you used for each of these use cases ?

Kevin Naidoo • Jan 10

Ollama with "PHI3-mini", "granite3-dense:8b", "mixtral" and a bunch of other small models. Paid models, I use OpenAI models like text-embedding-3-large, Whisper, TTS, GPT4o (and mini), etc...

For some coding tasks, I use Anthropic's API with Sonnet or Tabnine.

Recently, also using DeepSeek, and for some voice tasks, I use AssemblyAI.

Sarthak Sharma • Jan 13

Woah multiple models.

Got to know a lot of new ones.

You use them on cloud or locally?

Kevin Naidoo • Jan 13

Tabnine is probably the only local one, the rest are used in production. In the case of Ollama models that's a GPU server, I am running on prod, rest are just APIs to OpenAI/DeepSeek/Anthropic.

Often you'll find you need more than one model, the smaller models can perform niche tasks quickly and the bigger ones can do more complex tasks.

Azlan-Syed • Jan 10

Making my poor code look good honestly

Sarthak Sharma • Jan 10

😄 How?

Azlan-Syed • Jan 10 • Edited

Well just to make it a bit fast, like a bit milisecond better, at least i can rely on ai for taking out the trash btw your from india 🇮🇳 (me too)

Sarthak Sharma • Jan 13

Hahaha quite common use case I would say.
Oh that’s great. Which part and how long you been a developer?

Azlan-Syed • Jan 13

Well not certified, since I am still a teen, started coding stuff at 12, also had to cover up schooling stuff too

Andrew McSillyone • Jan 9 • Edited

Who do you think wrote all of my websites?
...chatgpt

Just kidding! However, we use AI, but remember that in about 30 years, AI will probably replace all of us on this forum!

Sarthak Sharma • Jan 10

Not really 😅 You will find here

Riikka Koivisto • Jan 13

I'm a bit of a grump in terms of AI usage, but of course it's seeped into my life slowly.

With work especially I am pretty hard opposed to AI taking over my creative processes, even just simple coding, because I feel like if the commit has my name on it, I better have an absolute grip on the code. Lately I've experimented with letting AI fill in boilerplate-y code, such as generating Laravel models from migration files I've designed. Tabnine does this pretty well, but what I found was that due to my issues with handing over control, I spent the same time checking that I would have spent writing.

Outside of work I use Perplexity for web searches, the fact that it not only gives me an explanation but also cites sources is one of the biggest reasons I've grown to like it. It's the same reason why I use Arc Search (and sometimes Perplexity) on my phone as well.

I don't let AI into my files (not explicitly, anyway..) nor do I give it any kind of info about my finances, that seems way too far into privacy invasion. I also detest that people enthusiastically give all sorts of AI-powered apps or sites their info, history, even voice and face, with little to no regard about their own privacy.

Sorry for the mile-long reply, thanks for reading! :)