🇲🇽 Digital albañil. Trip-hop. NuPhy keys. Café con leche at -20°C. Open source at @pressbooks
Joined April 2009
- Tweets 32,430
- Following 2,032
- Followers 1,794
- Likes 40,503
4,118 Photos and videos
Pinned Tweet
Apr 2
#CMS are dead.
I've been thinking for a while that dynamic CMS pages were deprecated a long time ago. We spent several hours as developers trying to make every website piece dynamic, naively thinking the end user would actually use all of it.
2
4
837
⌥ agentic~human retweeted
Jun 13
The new beta Claude Code model switcher
33
330
5,762
197,253
Jun 12
I can't stand Claude Code's TUI is extremely bad It's unreadable I guess that's the point of those "loopers" not read any of the output and just vibe loop.
@opencode is incredible it feels like something built by someone that cares about DX.
1
67
Jun 11
Hey @Montreal @monlaferte is exactly the good stuff you are missing for the Jazz Festival youtube.com/watch?v=vAgdNWiz…
34
⌥ agentic~human retweeted
Jun 8
i forgot everyone in apple keynotes have the personality of the hive in Pluribus
41
162
3,978
156,411
⌥ agentic~human retweeted
Jun 8
Apple has fixed the window corner inconsistency in macOS 27, my eyes can finally rest!
2
4
137
8,278
⌥ agentic~human retweeted
Jun 8
Siri AI can now create reminders and start timers 🤯
164
29
1,842
194,742
⌥ agentic~human retweeted
Jun 6
La FIFA a partir del jueves:
68
4,953
75,200
611,451
⌥ agentic~human retweeted
Parece un episodio de The Office 😭
285
1,075
10,983
422,805
⌥ agentic~human retweeted
Jun 1
El gobierno mexicano viendo que estamos a 10 días del mundial.
46
5,566
57,457
503,124
⌥ agentic~human retweeted
Jun 1
We are in a golden age where, if you are good at systems and understanding, AI increases your abilities by an order of magnitude. But if you are not good at it, you just spin your wheels and end up nowhere helpful
123
248
3,172
97,876
⌥ agentic~human retweeted
Jun 1
This is the first agent-era version of “naming things is hard.” The dangerous part isn’t the keyword, it’s when one vague term silently flips the runtime from linear help into orchestration mode.
1
1
352
⌥ agentic~human retweeted
May 31
How it feels to type in ur email and password with a remote
345
41,990
439,016
4,908,139
Anthropic CEO right now:
May 27
JUST IN: Sam Altman says AI probably won’t trigger the “jobs apocalypse” he once predicted.
74
841
24,775
2,617,577
⌥ agentic~human retweeted
May 28
Weird thing about LLMs: "incorrect responses" are more expensive than correct ones.
If I go to a restaurant and they screw up my food, they usually refund me and remake the meal.
If an LLM gets stuck on a problem, it runs around in loops, burning tokens and costing money.
156
106
3,330
175,877