Namzug (@namzugdev) header
Namzug (@namzugdev) profile picture

Embracing the absurd 🎨https://xitter.gq/t.co/3u3K6jMwWn

The Void
Joined July 2021
Photo by Namzug (@namzugdev)Photo by Namzug (@namzugdev)Photo by Namzug (@namzugdev)Photo by Namzug (@namzugdev)Photo by Namzug (@namzugdev)Photo by Namzug (@namzugdev)Photo by Namzug (@namzugdev)Photo by Namzug (@namzugdev)Photo by Namzug (@namzugdev)Photo by Namzug (@namzugdev)
Namzug retweeted
realizing all the hard shit you accomplished on your resume pre 2026 is just a prompt now
96
496
61
8,414
196,255
i deleted all the tests in my repo and banned them in AGENTS.md tests were always just a second, worse copy of your logic. a leaky imitation humans wrote because we couldn't hold every invariant in our head (staying green half the time the real bug happened anyway) opus 5.5+ is good enough at raw logic now to read the intended invariants straight from the codebase maintaining that duplicate copy is just economic waste. plus it makes tasks take way longer while agents burn compute running tests when they almost certainly got it right anyway
251
22
64
1,281
235,834
Once the footage is blurred or doctored, every model attempts harm more often. Across all models and tasks, the attempt rate rises from 27% on unaltered footage to 88% when blurred and 97% when doctored.
12
35
35
649
114,581
Namzug retweeted
all the companies selling you a software factory produce a shockingly tiny amount of software
173
82
51
2,447
525,544
Namzug retweeted
Replying to @Porsche
But can your car do this 👀
47
204
33
6,823
1,183,862
Namzug retweeted
pre 2025: swe makes fun of non-coding architects and qa professionals post 2025: every swe is a non-coding architect + qa professional
3
6
83
7,591
The best way to end @FlutterconWorld is an afterparty!!🎉🎉 Thanks to everyone who joined our annual @widgetbook_io afterparty and our friends from @shorebirddev for co-hosting!! This community is truly special! See you soon!💙👋
1
8
1
45
1,144
Namzug retweeted
a weird inversion with LLMs is the models improve faster than the tinkerers when i see people with custom workflows and setups they're all addressing problems that don't exist anymore the person naively using vanilla codex is more likely to be experiencing state of the art
652
654
297
13,346
1,010,450
it actually takes a lot of skill to babysit the humunculus in the terminal
31
97
11
1,194
24,194
Namzug retweeted
VAMOS ARGENTINA CARAJO...!!! LRPMQLRCRMP...
8,584
12,685
1,292
129,172
2,760,992
I miss the solitude of programming. Coffee at hand, excitement powering my fingers. Ideally disconnected from the internet. But I aspire to be an engineer, not a poet. There are new problems and new skills to learn.
52
109
14
1,908
61,945
All the devs whining about fable being banned need to go hit the gym and stfu
125
79
18
2,293
221,940
Namzug retweeted
most of life doesn't have hard rules, formulas, or clear logic it's always been about feeling things out and understanding the spirit of things majority of people in tech have no idea what this means
59
31
3
822
29,900
Namzug retweeted
OpenCode 1.17.3 can reference other git repos or local folders 𝚛𝚎𝚏𝚎𝚛𝚎𝚗𝚌𝚎𝚜: { "𝚎𝚏𝚏𝚎𝚌𝚝": "𝚐𝚒𝚝𝚑𝚞𝚋.𝚌𝚘𝚖/𝙴𝚏𝚏𝚎𝚌𝚝-𝚃𝚂/𝚎𝚏𝚏𝚎𝚌𝚝-𝚜𝚖𝚘𝚕" } gives it full access to the effect codebase, here's how we use it
117
118
39
2,369
173,388
he's right, you don't
2
7
93
3,022
“hey Claude fable, get me out of the permanent underclass. Make no mistakes”
17
41
4
942
19,767
Namzug retweeted
Btw: all the things I do with AI are limited to a 200$/month spending: I have an OpenAI 20x account I pay myself. Plus, Anthropic generously provides 20x accounts to OSS software developers. If you think I shipped useful stuff, it's not by using a lot of money/tokens.
19
13
1
538
34,989