Indie (Thinking Mode) 🤔 | Data Scientist | I used to teach Machines, now i just talk to them 😬 💻

Joined July 2017
9 Photos and videos
May 21
That’s why I prefer Python over JS
> open X > your codebase has leaked > your NPM packages are fucked > your framework has security issues
1
1
18
May 18
Studied about SEO, how it works and how to do it over the weekend… guess that’s a weekend well spent. #consistency #onepercent
3
32
May 16
It’s fascinating that no matter how many successful projects and successful Indie developers you study. It matters only so little… All of them say this one thing: Knowing doesn’t matter, only building does… because every journey was, is and will always be different…
3
32
May 14
In past few days i have been trying to study what successful Indies built, India and Outside in past 2-3 years. There’s a common pattern among new guys trying to copy the exact same thing with different branding… Does that work?? I am not seeing it… what do you think??
4
36
May 13
95% of your thoughts are repeated daily… 🤔 #selfmusings
2
45
May 13
I don’t have a product. I don’t have a niche. I barely have a plan. But I’m showing up anyway and figuring it out in public. Let’s see where this goes.
1
13
May 13
Tons of useless information on the feed, it’s tedious skim through and find something genuinely useful
1
8
May 12
Well 🤔
12
May 12
This is exhausting!!
7
May 11
Wondering if i am procrastinating more or less after i started using LLMs #claude #chatgpt @grok
1
14
May 11
Boring is better
15
May 10
Maths is fun… !! 🤩
14
Mar 22
3/3Also shipped: — Guided JSON (constrained decoding) → parse failures near zero — Prefix caching → faster TTFT on repeated queries — Persistent HTTP connection pooling → cuts loopback TCP overhead
18
Mar 22
2/3Qwen3 has a "thinking mode" — silently injects <think> blocks before JSON output, breaking all parsing with zero error indication. Disabling it needs TWO flags: --reasoning-parser qwen3 --default-chat-template-kwargs '{"enable_thinking": false}' Miss one → thinking re-enables
15
Mar 22
1/3Migrated a prod NL-to-SQL system from llama.cpp → vLLM yesterday. The migration took 2 hours. One Qwen3 gotcha took longer.
11
VR retweeted

8,692
46,027
301,032
187,138,022
4 Dec 2025
My feed is full with launches everywhere, but most of those are just doing same things again and again. Like for example: Everybody seems to be building cross platform posts app… I mean why?? Is there something that I don’t know?? Happy to learn…!!
1
5
66
4 Dec 2025
Are ppl still building AI chatbots??
19
4 Dec 2025
Back to basics
3
51
26 Oct 2025
Now then, Tenants can log in, create an entity, and see it appear in the dashboard. Dummy works!! Took a short break for Holidays, now back to the process.
1
29