Building @insta_wp @insta_pods. Tinkerer. Father.

Bangalore, India
Joined January 2009
Include

Only show posts containing:

Exclude

Hide posts containing:

Time range
-
Minimum likes
Vikas Singhal
@vikasprogrammer
22h
It's crazy how much you can get done with prompt engineering and chaining models output. @insta_wp Studio.
3
11
661
Vikas Singhal
@vikasprogrammer
Sep 26
Replying to @marc_ibrahim
team fortress 2 !!!!! pls
1
69
Vikas Singhal
@vikasprogrammer
Sep 23
Replying to @mahdiali_
1
1
63
Vikas Singhal
@vikasprogrammer
Sep 23
Replying to @AdmireTheWeb
Yes v0 or Lovable for WordPress. Soon available for testing. Publish to instawp in 1-click.
71
Vikas Singhal
@vikasprogrammer
Sep 23
InstaWP Studio (screenshots) - Choose a design direction - Generate page/website - Edit as human/agent. - Publish
4
1
10
833
Vikas Singhal
@vikasprogrammer
Sep 22
prompt -> website
97
Vikas Singhal
@vikasprogrammer
Sep 21
Replying to @AvinashDalvi_
Lovable for WordPress, in its full capacity.
1
1
75
Vikas Singhal
@vikasprogrammer
Sep 21
InstaWP Studio! (coming soon).
2
3
24
1,074
Vikas Singhal
@vikasprogrammer
Sep 8
Yes already fixed for connect plugin
2
32
Vikas Singhal
@vikasprogrammer
Sep 7
Running a 180-billion-parameter model on a single box that sits on a desk. The trick: 51.2B of those parameters are a lookup table that's never multiplied — only read. So it lives on the SSD, not in memory. That leaves 125.7B of actual compute, which fits in 128GB. Fed it a 192,049-token document. Prefilled in 116 seconds. Found the needle I'd hidden at the halfway mark. No cloud. Nothing leaves the room.
You want more? I have more ⚡️ Qwen3.8-Flash-Next on a single NVIDIA DGX Spark just got even better - Prefill at 8k is now 24.7% faster - Single-stream prose: ~47 tok/s, up from 44 - Fixed a speculative drafting bug that could cause up to a 24% drop in decode performance in some cases Another *interesting* update coming tomorrow. Get it here: github.com/MiaAI-Lab/Qwen3.8…
4
642
Vikas Singhal
@vikasprogrammer
Sep 6
Interesting only ~17% are thinking about alteratives due to security issues popping up in WP. cc @WPTutz
5
1
8
1,437
Vikas Singhal
@vikasprogrammer
Sep 3
Replying to @0xBakeer
Pair that with github.com/vikasprogrammer/w… and they can communicate over network in private.
1
3
120
Vikas Singhal
@vikasprogrammer
Sep 2
When even Claude users say “I don’t use anything else,” we know we’re doing something right. 😎
1
7
492
Vikas Singhal
@vikasprogrammer
Sep 1
Replying to @WPTutz
Posted the exact same poll today. Great minds think alike.
1
3
265
Vikas Singhal
@vikasprogrammer
Sep 1
With all the recent WordPress/plugin security issues, has your trust in WordPress taken a hit?
18%Considering alternatives
56%Just another phase for WP
26%My security stack works
34 votes • Final results
2
429
Vikas Singhal
@vikasprogrammer
Aug 31
Ever wondered how Sonnet, DeepSeek and Gemini differ on the exact same prompt? Me too. So I built this. One prompt, every model, side by side github.com/vikasprogrammer/c… Open source, BYOK.
4
1
17
1,405
Vikas Singhal
@vikasprogrammer
Aug 30
Hooked my new M5Stack Tab5 with the Nvidia DGX Spark. The application built is known as Sparky (build by claude). It is a helpful learning body which is operated by the new qwen3.8-flash model. Tab5 -> openwebui -> llama.cpp -> qwen3.8-flash-next Q4 (262k context window)
1
8
863
Vikas Singhal
@vikasprogrammer
Aug 30
Has somebody figured out how to tune Claude (cli)'s Technoblabber output? It just takes a lot of mental bandwidth to read two pages of output and then take a decision.
6
8
1,313