Harsh☄️

GSoC '26 @Joplinapp
building AI systems that scale
LLMs • pipelines • backend

[Harsh☄️ @Harsh16Gupta]

June recap:

- gsoc week 5 completed. everything is going well and I'm currently 2 weeks ahead of the planned timeline.
- completed most of the ai/ml from kirat's bootcamp.
- working on a saas.
- not happy with myself. I know I could have been more productive this month.

[Harsh☄️ @Harsh16Gupta]

@ybhrdwj Bhai phone ke liye responsive bana do

[Harsh☄️ @Harsh16Gupta]

@KESCoHQ @UPPCLLKO You people haven't contacted me till now
Also there is no electricity in Nawabganj area from last 5 hours

[Harsh☄️ @Harsh16Gupta]

@KESCoHQ @UPPCLLKO Done

[Harsh☄️ @Harsh16Gupta]

I like this banter

[Harsh☄️ @Harsh16Gupta]

into the final stretch

[Harsh☄️ @Harsh16Gupta]

One of my best decision were to invest in ai stocks.

[Jensen Huang @JensenHuang]

AI at the final frontier 🚀

[Harsh☄️ @Harsh16Gupta]

Opinion:

I don't think the question is "Graph DB or Vector DB?"

The real question is: How do we orchestrate them efficiently?

Still experimenting with retrieval strategies, context fusion, and tool-calling agents. Feels like there's a lot more to optimize.

[Harsh☄️ @Harsh16Gupta]

@Flipkart @flipkartsupport
How are the answers related to my query?

[Harsh☄️ @Harsh16Gupta]

@flipkartsupport
Why am I getting a higher price when logged in?

[Harsh☄️ @Harsh16Gupta]

Now what the heck is Offer Handling fee?

Due to these reasons I love amazon, never seen any such unnecessary fee there.

[Harsh☄️ @Harsh16Gupta]

@flipkartsupport @Flipkart
Look into this

[Harsh☄️ @Harsh16Gupta]

@flipkartsupport
Why am I getting a higher price when logged in?

[Harsh☄️ @Harsh16Gupta]

@flipkartsupport I am not receiving reply there

[Harsh☄️ @Harsh16Gupta]

https://t.co/awYZ21h68N

[Harsh☄️ @Harsh16Gupta]

Nice Read

[Harsh☄️ @Harsh16Gupta]

bad news

[Harsh☄️ @Harsh16Gupta]

@grok

Analyze my tweets, profile, and interactions and respond with the following:

Gender:
Sexuality:
Age:
Mental age:
Hobbies:
Personality disorder:
IQ:
Qualifying adjective to describe me:
5 favorite things:
5 things I don't like:
My partner according to 𝕏:

[Andrej Karpathy @karpathy]

We're starting to leave the territory where you'd test an LLM by e.g. "create an svg of pelican on a bicycle". As one idea to generalize it, I was interested what Opus 5 would do if I gave it the first paragraph of the Lord of the Rings, a 1M token budget (~$10) and asked for three js render of it. Opus went off for ~2 hours and wrote 5500 lines of code that (procedurally) rendered the story. It's kind of janky but fun. But it's a bit mindboggling that the LLM has to place and orchestrate various polygon assets in (x,y,z) coordinates and write code that animates it all, and that it even does anything at all.

I also like this kind of examples because no one in their right mind would ever spend the time to write something this custom but LLMs have all the stamina and patience in the world, so it's an example where we go from "no one would ever do this" to "sure, why not, it's ~free". There might be a lot more. But I'm excited about creating hyper custom worlds that you can imagine dropping players into, e.g. here to participate in the LoTR story as a spectator NPC, or one of the characters, or etc. Something like an ephemeral GTA of X on demand.

Last thought is that the domain of worlds/games exposes a weakness in LLMs: they can't easily audit their work because they aren't able to efficiently and natively perceive videos or play games within them. Here, Opus 5 had to very slowly and painstakingly take screenshots at different points, and it messed up a few times and created a bunch of jank. An example of raw capability (multimodal, gameplay) that I think is still quite lacking.

[DeepSeek @deepseek_ai]

🚀 DeepSeek-V4-Flash Official API is now LIVE in public beta!

🔷 We’ve massively upgraded its Agent capabilities—benchmark scores are now far surpassing the V4-Pro-Preview. Check out the massive performance leap below! 👇
🔷 The official V4-Flash now natively supports the Responses API format and is fully adapted for Codex!

Check out the configuration details in our official API docs: https://t.co/smCwQZMeiq

[Harsh☄️ @Harsh16Gupta]

@Bitflicker64 @shhhubhika Mere feed me bhi aa gaya
Teri wajah se