Atulya Rai

393 posts

Atulya Rai banner
Atulya Rai

Atulya Rai

@snehit70

I post what I’m learning in code. Linux, Neovim, AI/ML, and random experiments.

pwd Katılım Aralık 2025
136 Takip Edilen23 Takipçiler
Atulya Rai
Atulya Rai@snehit70·
@jayair This was bound to happen based on the quality and constant improvement of opencode
English
0
0
1
502
Jay
Jay@jayair·
OpenCode has grown 10x since the beginning of the year From 650K to 6.5M active users
English
89
65
2K
161.4K
vixhaℓ
vixhaℓ@TheVixhal·
I got fired from Anthropic today. It was my first job out of college, and they placed me on the Claude Code team. I was excited. It felt like I had made it. After getting settled in, I worked on my first PR and finally submitted it. Claude reviewed my PR and approved it. Along with the approval, it left a comment: “This code will be one of the biggest open-source contributions.” That confused me. I replied, “Why would it be one of the biggest open-source contributions? Our repository is private, isn’t it?” It responded, “Just merge the PR. You don’t have to think much.” And I merged it.
English
25
11
239
45.3K
Atulya Rai
Atulya Rai@snehit70·
@TheVixhal I had 3 projects using axios it was a close call for me .
English
0
0
1
167
Julius
Julius@jullerino·
Did the 2x Codex limits expire? Usage draining fasssssttt
English
88
5
653
108.6K
Atulya Rai
Atulya Rai@snehit70·
@thsottiaux Has the limits dropped for codex because after the refresh because its getting used faster for the same number of tokens.
English
0
0
1
24
Tibo
Tibo@thsottiaux·
Hello. We have reset Codex usage limits across all plans to let everyone experiment with the magnificent plugins we just launched, and because it had been a while! You can just build unlimited things with Codex. Have fun!
English
672
390
9.1K
918.1K
Yuchen Jin
Yuchen Jin@Yuchenj_UW·
hey friends! 👋 Only cool people are allowed to reply to this tweet obviously.
English
264
3
480
49.7K
Dmitry Korzhov
Dmitry Korzhov@korzhov_dm·
What if the voices we love didn't have to disappear? They don't have to.
English
226
30
248
375.4K
Ben Dicken
Ben Dicken@BenjDicken·
It finally happened. The agent dropped my database. AND I'M SUPPOSED TO BE THE DATABASE GUY.
English
153
48
2K
155.1K
vixhaℓ
vixhaℓ@TheVixhal·
How did the person who made the first clock know what time it was?
English
30
3
46
6.2K
dax
dax@thdxr·
i was at a wedding and someone told me they saw how opencode laid off 160 engineers begin is a menace
English
42
8
1.1K
108.5K
Atulya Rai
Atulya Rai@snehit70·
@dakshgup Hey do you guys offer student discounts or student packs ?
English
0
0
1
14
Daksh Gupta
Daksh Gupta@dakshgup·
we rebuilt our onboarding to be more visual, showing everything from the indexing process to how you can configure greptile to your liking
English
18
2
137
15K
Atulya Rai
Atulya Rai@snehit70·
@Pseudo_Sid26 At this moment folks should start flexing their aws invoices
English
0
0
1
20
Siddharth
Siddharth@Pseudo_Sid26·
I am using both claude and codex at the 20 dollar plan and I ain't running out with them. Just ran with claude weekly limit once that too when i was testing out claude with full extent and trying to understand its usgae. If he would have known coding, trust me this usage would reduce by 12x. Don't fool urself into using AI, its a helper, not a substitute.
Rob Hallam@robj3d3

This 18 year old literally has 12 $200 Codex plans. Here's exactly how he organizes them to build 100x faster: (we're cooked)

English
5
0
32
1.7K
Atulya Rai
Atulya Rai@snehit70·
@TheVixhal should have read it earlier would have helped me alot .
English
0
0
1
7
Paul Graham
Paul Graham@paulg·
@christineist Damn, I thought this was going to be about finding derivatives.
English
7
2
135
12K
christine
christine@christineist·
on differentiation, in passionate marriage
christine tweet media
Français
7
13
256
22.9K
Atulya Rai retweetledi
Atulya Rai
Atulya Rai@snehit70·
I type at 60 WPM. I speak at 158 WPM. That 2.6x gap kills context mid-session with a coding agent. On Mac, Wispr Flow fixes this. On Linux, nothing existed. So I built hyprvox. Dual STT engines, LLM merge, 882ms median, 39x faster than real-time.
Atulya Rai tweet media
English
1
1
4
106
Atulya Rai
Atulya Rai@snehit70·
The slow part was the waiting Now it is just the scroll. Hyprland shipped scrolling workspaces. I had already started looking at Niri. Hyprland got there first.
Atulya Rai tweet media
English
0
1
3
35