Juan Sepulveda

1K posts

Juan Sepulveda banner
Juan Sepulveda

Juan Sepulveda

@jsep_do

learning and enjoying life

Katılım Nisan 2019
237 Takip Edilen46 Takipçiler
Juan Sepulveda
Juan Sepulveda@jsep_do·
a good run this morning preparing for my first 10k
Juan Sepulveda tweet media
English
0
0
0
2
Juan Sepulveda
Juan Sepulveda@jsep_do·
@ctatedev no doubt this is impressive, but what it means design for ai agents?
English
0
0
0
415
Chris Tate
Chris Tate@ctatedev·
I built Zero in 3 days. I didn't expect it to compile. I didn't expect it to mostly self-host. I definitely didn't expect it to work at all. Inspired partly by Bun's rewrite to Rust, Zero started as an experiment. Honestly, the project says more about where AI is today than it does about the language itself. It took more than 3,000 agent tasks to get here, and it's still nowhere near ready for serious comparisons, benchmarks or evals. But the goal is bigger than the current result. The hope is to either create a new language with tooling designed for agents from the ground up, or take learnings and apply it back to existing languages and ecosystems. The ideas are simple: 1. Make languages (and new versions) easy for agents to learn, adapt to and fix on the fly, even when not in the training data. 2. Build a standard library comprehensive enough that most projects don't need external dependencies. 3. Create a tight, fast development loop that even small models can reliably work with. I've never wanted to create a programming language. But after repeatedly running into the same problems, safe but slow builds, fast but unsafe builds, agents struggling with new languages and version changes, wanting faster builds, smaller bundles and better DX, I started wondering: Could accelerated, agent-driven iteration produce a language and tooling stack designed around these constraints from the start? So Zero was born.
Chris Tate@ctatedev

Introducing Zero The programming language for agents. I wanted a systems language that was faster, smaller, and easier for agents to use and repair. Explicit capabilities. JSON diagnostics. Typed safe fixes. Made for agents on day zero.

English
57
15
374
53.8K
Tanner Linsley
Tanner Linsley@tannerlinsley·
Despite the “TanStack”-mention firehouse getting cranked 10,000x this week, I still insisted on reading every single one (not a bot!). Any single person would have probably gone insane, but I’m not alone! The people on my team are amazing (the open source ones and the ones that I live with). They kept me grounded and we got to work. Result? My dedication to this craft, this ecosystem, and its people are higher than ever before. Get ready for an awesome TanStack summer.
English
46
11
690
24K
Juan Sepulveda
Juan Sepulveda@jsep_do·
@mcuban great idea: let’s make the heavily subsidized tokens more expensive
English
0
0
0
5
Mark Cuban
Mark Cuban@mcuban·
We should federally tax Tokens at the Provider level. Not a lot. Less than 50c per million tokens. It will accomplish 4 things (at least ) 1. It will push the big AI players to optimize tokenization, caching , routing and localization Which will 2. Reduce energy usage. Saving them in energy costs more than what they paid in tax and reducing strain created by the growth in energy consumption Which will 3. Generate maybe 10 billion dollars a year to start, but over the next ten years could grow 30x to 100x Which will 4. Create a source of funding to pay down the federal debt or deploy, in response to the things AI brings that we don’t expect or don’t like At some point the models will pass it on to customers. Of course. That’s ok. Customers will have the ability to choose between providers. Or to do everything using open source models locally. Thoughts ?
English
1.9K
228
3.4K
688.6K
Rand
Rand@rand_longevity·
i mean lets be honest, if you are under 50 you and never gonna see that social security money you will just have to live with universal basic income
English
26
4
113
4.3K
Juan Sepulveda
Juan Sepulveda@jsep_do·
don't share password with anyone, if they are compromised you'll be vulnerable
English
0
0
0
9
Chris Tate
Chris Tate@ctatedev·
Introducing Zero The programming language for agents. I wanted a systems language that was faster, smaller, and easier for agents to use and repair. Explicit capabilities. JSON diagnostics. Typed safe fixes. Made for agents on day zero.
Chris Tate tweet media
English
220
112
1.7K
562.1K
Matt Pocock
Matt Pocock@mattpocockuk·
Long skills are such a red flag to me - Hard to audit (and therefore, trust) - Hard to edit (more text, harder to maintain) - Expensive to run (more text, more tokens) The shorter the skill, the better IMO
English
140
47
1.3K
74.5K
Dmitrii Kovanikov
Dmitrii Kovanikov@ChShersh·
I've seen man-made horror code bases much worse than the ugliest vibe slop you ever encountered
English
63
17
442
17.8K
Rand
Rand@rand_longevity·
what do you put in your morning coffee?
English
128
1
90
12.9K
Juan Sepulveda
Juan Sepulveda@jsep_do·
the Bun rewrite to rust is impressive
English
0
0
0
20
Juan Sepulveda
Juan Sepulveda@jsep_do·
this the best to create new projects
English
0
0
0
5
Adam Richard Turner
Adam Richard Turner@devadam88·
As a developer, in what time can you run 5km? 🏃
Adam Richard Turner tweet mediaAdam Richard Turner tweet media
English
74
0
52
17.6K
Juan Sepulveda
Juan Sepulveda@jsep_do·
I’ve just got layoff, time to convert into an AI bro
English
0
0
1
14
ThePrimeagen
ThePrimeagen@ThePrimeagen·
i regret to inform you that i have to learn python
English
576
164
5.9K
362.8K