Using Grok 4's video + voice for Starlink Mini setup instructions. https://t.co/35yCD5tADC
0
0
10
109
6
webpage built with Grok 4 Heavy. https://t.co/N1vLsluTNF
0
0
24
126
10
Grok4’s Ani explains paging in Linux. https://t.co/PwRgSRY1y0
0
0
13
99
15
You can use Grok 4's Bad Rudi to lean Mandarin. https://t.co/H4TZYI6fze
0
0
52
119
12
Grok4’s Ani explains Multithreading vs. Multiprocessing in C. https://t.co/RkuMAoGiE1
0
0
255
1.2K
165
For the love of the game. https://t.co/4GvIVGbmS8
0
0
186
7.6K
1.5K
Grok 4 is the smartest AI in the world. https://t.co/1HFEA8CzH8
0
0
36
127
22
Timeline cleanse. 14 Sorting Algorithms in 1 Minute. https://t.co/bPFoGjOzrP
0
0
2
33
4
Grok4’s Ani explains memory alignment for a union in C. https://t.co/zpySLYe1OZ
0
0
16
65
3
People keep asking if Grok 4 Heavy is better than Claude Opus. Opus is not even close, I canceled my Claude subscription.
0
0
237
2.3K
238
Grok 4 Heavy (left) V.s. Gemini 2.5 Pro (right)
Create a Turing-complete Scheme interpreter in C that supports lexical scoping, closures, continuations, and proper tail-call for tail recursion without stack growth.
Grok4 won. It wrote superior code.
Grok4 Heavy: 903 Lines of C code.
Gemini 2.5 Pro: 891 Lines of C code.
Both compiled!
The code from Grok 4 Heavy worked flawlessly.
The code from Gemini 2.5 Pro did not work even after multiple prompts.
Grok 4 Heavy: ~10 minutes single prompt.
Gemini 2.5 Pro: ~2-3 minutes per prompt after about 10 prompts I gave up.
Full Prompt👇
Show more
0
0
81
1.3K
126
Grok 4 Heavy is better than any other Model for coding. There is so much code that Gemini can't create no matter how many times you prompt it that Grok 4 will just one shot.
0
0
106
522
41
Grok 4 Video + Voice is able to identify GPUs by looking at the chipset. Pretty impressive. https://t.co/DK3ml02XZC
0
0
15
107
8
