Adhyaay Karnwal

1.8K posts

Adhyaay Karnwal banner
Adhyaay Karnwal

Adhyaay Karnwal

@AdhyaayK

15 and working on https://t.co/ktKproOFh2

Katılım Nisan 2025
237 Takip Edilen118 Takipçiler
Sabitlenmiş Tweet
Adhyaay Karnwal
Adhyaay Karnwal@AdhyaayK·
we're hiring petal is growing; we're looking for a GTM to help us land clients what we’re looking for: ↳ 6+ m experience in b2b sales ↳ strong outbound and closing abiliy ↳ real estate knowledge(optional) ↳ fun location: us (remote) comp: commission Dms open
Adhyaay Karnwal tweet media
English
0
0
7
666
Alok
Alok@analogalok·
This is the most hilarious thing I saw and did today Ran gemma-4-12B-coder-fable5-composer2.5-v1-GGUF locally with 8 GB VRAM at 20+ tok/sec Anthropic's Claude Fable 5 launched June 9. By June 12 it was banned. I can't access it. You can't either. But here's the twist: I'm running a model trained on its chain of thought at 20 tok/s on my RTX 4060 8GB. Locally. Offline. No cloud. No export control. Enter: Gemma4-12B-Coder GGUF (Q4_K_M) Base: Google's gemma-4-12B-it Fine-tuned on verifiable Python CoT data: - Primary: Composer 2.5 real reasoning traces (only passing solutions kept) - Auxiliary: Fable 5 used to redo the hard cases Composer missed. Every training example's reasoning led to code that actually ran. No hallucinated logic. Llama.cpp flags: -m gemma4-coding-Q4_K_M.gguf -cnv -ngl 44 -c 64000 -v (huggingface model link in comments) Flag breakdown: -ngl 44 → offload 44 layers to GPU (tune this for your VRAM) -c 64000 → 64K context window -cnv → conversation/chat mode -v → verbose output The irony writes itself. Anthropic spent weeks telling the world Fable 5 (mythos) is too powerful to release. Then released it. Then got banned from serving it, including their own researchers. Meanwhile: a Gemma 4 12B fine tune, trained on Fable 5's reasoning, runs fully offline on my mid range consumer GPU No API. No cloud. Just me and llama.cpp. This is why local AI matters. Check out the model's link in the comments. How's your experience been with this model?
Hugging Models@HuggingModels

Gemma 4 12B Coder is here and it's a game changer for local code generation. This GGUF model packs Google's latest gemma-4 architecture into a compact 12B size, perfect for running on consumer hardware. It's optimized for reasoning and thinking, making it ideal for developers who want fast, private coding assistance without the cloud.

English
63
145
1.6K
211.8K
Adhyaay Karnwal
Adhyaay Karnwal@AdhyaayK·
@calcsam Wait damn what happens to Mastra The last time I used it was like early 2025 or smth that’s crazy
English
1
0
1
149
Sam Bhagwat
Sam Bhagwat@calcsam·
We're excited to introduce Claude Code, Cursor, and Codex agents in Mastra. Starting today, Mastra is now a meta-harness:
English
27
20
192
23.6K
Daksh Gupta
Daksh Gupta@dakshgup·
introducing t-rex with t-rex enabled, greptile doesn't just review your PR, it runs your branch in a sandbox to find bugs. it mocks api calls, clicks around the UI, and writes + runs unit tests in our benchmarks, it caught ~20% more bugs than base greptile. most of the new bugs caught could not have been caught with more inference, they required code execution. t-rex is available in beta to all greptile users
English
26
13
381
41.5K
Scott Tolinski
Scott Tolinski@stolinski·
Just got access to the new Siri and not super stoked that it makes searching with Safari impossible from the home screen now. To do a web search you have to either hope it decides to show you Safari as an option here to open Safari itself.
Scott Tolinski tweet mediaScott Tolinski tweet media
English
3
1
13
3.9K
Adhyaay Karnwal
Adhyaay Karnwal@AdhyaayK·
yo @DevinAI @cognition my birthday's around the corner(5 days) could use some devin credits I just used mine up tryna make smth👀 special gift or smth yk yk
English
0
0
0
67
Mohamed Charfeddine
Mohamed Charfeddine@MohamedCha38349·
Day 20of posting content till I join @10x_apps team. This is the last video with this format( still just 3 days) . Hours of editing on this one, give it a watch.
English
8
4
20
969
Adhyaay Karnwal
Adhyaay Karnwal@AdhyaayK·
Just found a way to bypass the Siri waitlist
English
3
0
8
4.9K
Adhyaay Karnwal
Adhyaay Karnwal@AdhyaayK·
@whitekr_ On everything this gave me access I promise You can see that before recorded I tried something because I didn't believe it worked I was on the waitlist and my phone already had Apple Intelligence so maybe it was already available just needed to be unlocked to put me off the wait
English
0
0
0
42
WhiteKr
WhiteKr@whitekr_·
@AdhyaayK just lucky timing. this is not how it works. and if you still say it worked, of course.
English
1
0
0
47
Jerrick Hakim
Jerrick Hakim@jerrickhakim·
Alls what I do it run agents from my iPhone now. I’m really a vibe coder.
Jerrick Hakim tweet media
English
2
0
1
524
Adhyaay Karnwal
Adhyaay Karnwal@AdhyaayK·
@dunk3ey But I never got access I was on the waitlist (and doing this gave me access) I promise that i was on the waitlist before trying this and it worked U gotta be on iOS 27 and on the waitlist I think And already have Apple Intelligence/your phone being compatible
English
0
0
0
270
duke.
duke.@dunk3ey·
@AdhyaayK I’m in the US, it just says I need access. It works if you already got access normally
English
1
0
3
182
Adhyaay Karnwal
Adhyaay Karnwal@AdhyaayK·
You can bypass the Siri waitlist if you’re in the US by typing this
English
2
0
1
857
Adhyaay Karnwal
Adhyaay Karnwal@AdhyaayK·
@whitekr_ it literally worked tho (i recorded it after i already tried the hack bc i realized it actually worked)
English
1
0
0
391
duke.
duke.@dunk3ey·
@AdhyaayK Doesn’t bypass, obviously.
duke. tweet media
English
1
0
5
614
Saksham
Saksham@sxmawl·
genz cold DMs are refreshing!
Saksham tweet media
English
63
3
639
38.3K
Ben Aratame
Ben Aratame@benaratame·
after hitting $3M ARR, 2.5B+ views, 37K+ App Store reviews, and millions of app downloads i wrote an X article on how i launch and scale UGC programs best outcome of my UGC programs? a comment from giannis
Ben Aratame tweet media
Ben Aratame@benaratame

x.com/i/article/2062…

English
3
3
69
10.8K