Juan Cruz Martinez

6.7K posts

Juan Cruz Martinez banner
Juan Cruz Martinez

Juan Cruz Martinez

@jcmartinezdev

Deep dives on engineering careers and AI’s real impact on developers. Writing The Long Commit on Substack. 20 yrs building software. @Auth0

Bavaria, Germany Beigetreten Kasım 2007
265 Folgt1.5K Follower
Jess Temporal
Jess Temporal@jesstemporal·
Caption this 😂
Jess Temporal tweet media
English
2
0
1
77
Chris Sev
Chris Sev@chris__sev·
Another way to say "i am deep dive vibe coding with @claudeai" ... i'm whirlpooling
Chris Sev tweet media
English
2
1
7
833
Juan Cruz Martinez
Juan Cruz Martinez@jcmartinezdev·
Readwise is this tool I almost never access, that works in the background and is the backbone of my content and what I read. And now, more agentic than ever. It’s great to see all the good work they are doing! Innovation++
Readwise@readwise

New: Readwise for @openclaw Save anything with one click from your browser or phone: articles, tweets, books, youtube, podcasts, newsletters, more. Your claw now has instant access to that full library as markdown. Easily search and actually stay on top of it all.

English
1
1
11
1.9K
Juan Cruz Martinez
Juan Cruz Martinez@jcmartinezdev·
"AI is making developers more productive." The data tells a different story: code output up 59%, release frequency flat, PR review time up 91%. We're producing more code and shipping the same amount of software. That's not productivity. That's a faster hamster wheel. I've been thinking about what 30 more years of this looks like: newsletter.thelongcommit.com/p/i-have-30-ye…
English
0
0
0
22
Juan Cruz Martinez
Juan Cruz Martinez@jcmartinezdev·
I know I'm behind... but I'm now watching Severance, just watched two episodes, something tells me that this weekend I won't sleep until I finish the two seasons.
English
0
0
0
21
Juan Cruz Martinez
Juan Cruz Martinez@jcmartinezdev·
Something I keep noticing: the engineers panicking most about AI replacing them are the same ones who haven't shipped a side project in five years.
English
0
0
0
16
Juan Cruz Martinez
Juan Cruz Martinez@jcmartinezdev·
@trq212 Like with some high energy consumption products, Claude should come with a feature "Run this prompt when tokens are cheap"
English
1
0
0
101
Thariq
Thariq@trq212·
We've landed a lot of efficiency wins to offset this, but ~7% of users will hit session limits they wouldn't have before, particularly for pro tiers. If you run token-intensive background jobs, shifting them to off-peak hours will stretch your session limits further.
English
81
17
968
374.7K
Thariq
Thariq@trq212·
To manage growing demand for Claude we're adjusting our 5 hour session limits for free/Pro/Max subs during peak hours. Your weekly limits remain unchanged. During weekdays between 5am–11am PT / 1pm–7pm GMT, you'll move through your 5-hour session limits faster than before.
English
2K
455
6.8K
6.2M
Juan Cruz Martinez
Juan Cruz Martinez@jcmartinezdev·
@trq212 I guess for things like these it's good to live in the EU, and finish working before SF gets up 😂
English
0
0
0
31
Guillermo Rauch
Guillermo Rauch@rauchg·
1961: We should ship a CLI 2026: We should ship a CLI
Guillermo Rauch tweet media
English
153
194
2.6K
91.3K
Juan Cruz Martinez
Juan Cruz Martinez@jcmartinezdev·
@elvissun I'm completely ignorant lol, but is the mac studio a lot more powerful than the mini with same processor?
English
0
0
0
46
Elvis
Elvis@elvissun·
mac studio for zoe just arrived m4 max, 128gb ram - enough for a fully parallelized swarm of 10 agents running locally thinking about live streaming the setup. would anyone watch? maybe we can also figure out how to get zoe in the chat
Elvis tweet media
Elvis@elvissun

mac dilemma update (73 comments later): going with M4 Max 128GB. now. here's why: 1. opportunity cost - every day my agents are bottlenecked is a day I'm not shipping (wwdc in june is 5 AI years away) 2. pre-AI pricing won't last - apple priced these before AI agent demand 3. vertical scaling = focus - managing network I/O across multiple minis is time I'd rather spend building 4. local = control - no rate limits, no API outages, full autonomy 5. memory > compute - RAM is the bottleneck for agent swarms, not CPU my plan now is to use the studio to power my agent swarm but rely on cloud models (codex 5.3 mostly), but one comment that stuck with me from @HEXtheantidote: "running a local model is the only way for them to achieve true autonomy" local models aren't there yet. but in 12 months? having a self-hosted AI might be as normal as having a router. Mac is the body. agent is the soul.

English
54
3
215
30.6K
Eddie Jaoude | Open Source | GitHub Star
What do you think of my office today? I am launching ScreenRecording Pro on Product Hunt with 50% discount on the one off Lifetime payment 🎉 Stop making boring videos! Easily start making engaging videos with features like: zoom, text on screen, annotations AND MORE! 🚀 Support me on this post and on PH... 🙏 producthunt.com/products/scree…
Eddie Jaoude | Open Source | GitHub Star tweet media
English
52
28
93
14.5K
Pratham
Pratham@Prathkum·
By 2030, everyone will have their own software tailored to their needs and use cases.
English
48
11
153
7.5K