hectorip (@HectorIP) header
hectorip (@HectorIP) profile picture

Desarrollo software. Creador de @TheDojoMX. I’m running out of time.

CDMX, México
Joined August 2010
Photo by hectorip (@HectorIP)Photo by hectorip (@HectorIP)Photo by hectorip (@HectorIP)Photo by hectorip (@HectorIP)Photo by hectorip (@HectorIP)Photo by hectorip (@HectorIP)Photo by hectorip (@HectorIP)Photo by hectorip (@HectorIP)Photo by hectorip (@HectorIP)Photo by hectorip (@HectorIP)
Mañana durante el #CÓDIGOFEST de @codigofacilito, @HectorIP y yo hablaremos sobre si deberíamos seguir leyendo y escribiendo código, o esa tarea debería ser totalmente de los agentes.
2
6
288
There will never be a formal proof method that ensures a program behaviour matches what’s in your head
54
28
11
425
19,829
I’m not overthinking. Things are overhappening.
212
15,412
409
67,441
1,079,710
hectorip retweeted
There is no moat.
153
308
64
9,782
400,993
hectorip retweeted
“We’ve patched every single vulnerability, we don’t understand why we’re still getting breached?”
32
124
4
1,570
30,991
everyone that uses more tokens than me is just shipping slop and everyone that uses fewer is ngmi
19
99
6
1,980
37,112
hectorip retweeted
The real AI psychosis is thinking "this is just another tool" or "it's just a stochastic parrot" and "humans still need to review every line". You gotta snap out of it.
553
476
165
7,806
396,426
People romanticize pre-agentic programming like spending years memorizing APIs, fighting build systems and manually gluing together libraries wasn't a soul-crushing waste of human potential.
35
73
5
1,041
18,735
hectorip retweeted
Roughly the token allocation for each window on the $200 plans. Yes that 5h line is indeed above the other 7d line.
36
25
7
746
50,461
hectorip retweeted
very weird thing happening rn technical people are sad, they think their skills are now useless non-technical people are desperately wishing they were more technical so they could use agents better
1,568
2,406
682
36,947
1,963,095
hectorip retweeted
Unpopular opinion: the people getting the most out of AI are the ones who could do the work without it.
337
527
135
5,979
228,251
AI makes infinite software possible: if you want something to be different, you simply ask. Would you like your grocery list to be sorted by aisle? Ask. For programmers, that’s a massive reduction in friction. For non-programmers, it’s a revelation.
3
3
20
1,230
It’s kinda crazy to me that we melt sand down, clean it to 99.99999% purity, literal wizards have to draw it slowly into an ingot, we cut it, inscribe a hundred billion little on/off switches on it, and when you run electric current through it you can do basic arithmetic, which when you do enough of it can do any math on the planet, and which describes reality well enough that we can teach it the ontological meaning of words and their distance from each other on a high-dimensional space, and if you ask, it can tell you what word comes next and that apparently is powerful enough that if you do it a hundred billion times it’s the smartest thing to ever exist oh yeah and we use this primarily for email
217
973
108
12,326
448,690
Do not learn tomorrow what you can learn today and do not worry about what you need to learn tomorrow while you are still busy learning what today offers
1
2
30
738
Programmers, engineers, and mathematicians who hate AI loved solving puzzles not problems.
104
210
30
3,910
58,949
hectorip retweeted
pretending your written code is less slop than frontier models is a huge cope btw
139
486
49
10,021
199,551
I'm old enough to remember when 'C++ slop' was the battle cry of 'real' coders. Then it was 'Unity slop' and 'Unreal slop' from those who thought hand-rolled engines were superior in every way. Now it's AI slop. People draw a line on the abstraction hierarchy below which they are happy to automate the tedium. The line just moved... that's all. Skilled people will still make superior software. We have been inundated with low quality slop since the birth of digital distribution decades ago. It's nothing new.
55
77
10
662
17,309
Llevamos décadas construyendo software con código mediocre, bugs ancestrales, hacks sobre hacks, tests a medias, TODOs olvidados, parches temporales que se volvieron permanentes y código que nadie se atreve a tocar. Y ahora resulta que nos preocupa confiar en código que no entendemos porque lo escribió una IA. Como si lleváramos décadas entendiendo perfectamente el código que escribimos nosotros.
126
188
29
1,493
48,553
Amazing how quickly we went from "oh no LLMs are going to flood the Internet with insecure code" to "oh no LLMs have discovered the internet was already flooded with insecure code"
51
662
44
9,411
94,407
Unpopular opinion: your results with AI largely depend on how smart you are
706
1,713
318
18,768
501,001