Javier Rivero (@_javierivero) header
Javier Rivero (@_javierivero) profile picture

ai community lead ✷ operations @stripe ✷ ambassador @spacexai

Joined May 2007
'Vibecoding' used to be a derogatory term until engineers realized there was no going back from agentic coding Now they silently rebranded it as 'building' needing a word that was just ambiguous & inclusive enough but still felt like serious craft We’ve come a long way
2
2
249
Model hallucinations
1
141
It seems new models default to over-engineered solutions for small problems Spent the entire morning optimizing and cleaning up my skills & subagent rules (I think I removed a total of 10k lines) A ton of tool calls & extra validation steps are usually built in for things that just need a simple run (ie sql queries) or a superficial analysis Token efficiency will become more relevant as budgets get tighter
1
1
222
Can’t put this one down
1
100
Autumn is such a beautiful time to visit NYC
4
307
I’ve been seeing absurd efficiency gains with AI lately But trying to understand why I was so surprised led me to a realization When working with AI, it’s easy to credit the models for almost all of it. In reality, the wins came from a much deeper exercise in first-principles problem solving It’s tempting to jump straight into the prompt box and feel like an efficiency god watching a model "think" for 15 minutes. Yet after a few stretches of idle waiting, I wondered: which parts of this process should be optimized or killed altogether? Because of the immediate feedback loop with AI, we've stopped thinking about spotting basic overprocessing, waiting, or unnecessary handoffs, we blindly optimize for raw speed. But realistically, at least 60% of our 10x gains was just a classic continuous improvement exercise. AI simply handled the boring execution (triaging, tagging, parsing transcripts, etc) There is plenty of hype around AI automation, but from what I can see, most of it is just putting a faster machine processing pure operational waste
2
244
Won't even be looking at the price tag for this one
You will no longer be responsible for your actions. Tomorrow.
1
190
Link is now available to use with your Muse agent in Mexico!
🤖 Made with AI
1
22
667
Excited to finally try this out
1
4
381
Sunday hallucinations
1
10
439
Today I was lucky enough to see an Edward Hopper painting up close and couldn’t help but think that there is a fine balance between skill & being able to communicate an idea when it comes to making art The thing is, some people mistake "intention" for "good art” The thing is, there is a lot of bad art out there that people blindly accept as good just because it’s on a museum wall — they’re usually too afraid to speak their minds out loud for fear of retaliation from the herd.  If an art piece has to overexplain itself (Pollock) to prove its worth, that’s already an indicator that either the skill or the idea is missing True art requires both at the same time Please stop arguing in favor of bad art just because it has "intention." Intention alone will never resonate with anyone, whereas an idea communicated skillfully (like Hopper does here) will be obvious to even the most casual observer
8
415
SpaceXSI Compile NYC was so much fun! Apparently im in the top 8% of earliest @cursor_ai adopters, hence the badge 🫡
5
1
81
2,037
Friends who gift books are the best type of friends Thank you @theesabina !
1
6
1,090
Gemini’s Argon does this annoying thing where it builds web artifacts for simple answers and it’s driving me crazy Any ways to turn this off?
317
I believe subsidized ai runway will last for another year or so
JUST IN: Replit CEO Amjad Masad warns users of subsidized AI subscriptions to "get ready to get rug pulled" as companies face unsustainable operating costs.
244
Ridiculous how accurate his vision of the future was
150
Such a great read
10
404