we're on track to building the best dspy powered llm framework in the typescript world

night ride vancouver

all this talk in canada about natural resources, which parent wants their kids to be a freakin miner sad shit vs a kid in texas going to work at the literal star base taking humanity to mars

thought about this a bunch so many businesses prey information asymmetry and lazyness

my feed is like one big model demo showcase

"maybe if you took off those prada shade there might be something to be pradabout" -- @fellahadid

I'm building a harness fit for openneko (openneko.app) from scratch using the axllm.dev framework

the death of the snkrs app meta is an incredible case study in artificial scarcity backfiring

keeping the cool stuff out of stock and flooding the outlets with uninspired garbage is peak mid-wit optimization by nike

I made a computer vision tool for rock climbing analysis in 3D using iPhone LiDAR! Having learned a lot from sharing my previous rock climbing demos, I realized that a lot of rock climbing analysis is well-suited for 3D. Even something as simple as supporting videos where the person filming moves with the climber requires 3D information. To get the depth information, I used my iPhone 15 Pro’s LiDAR depth sensor through my local iPhone app. I found that the depth measurements help a lot. I think the holds activation is better, and I like the final view of all of the holds in 3D. It’s also interesting to see the distance traveled in meters. Plus, it looks cool and it feels like a video game 🙂 In short, I think this new demo is an improvement in that climbers can see the real-world distance traveled and a visualization of which hand and foot activated which hold. I recorded the video and depth measurements from my iPhone app, and I ran the rest of the analysis on my computer. I used ViTPose+ Large for pose estimation and SAM 3.1 to segment the holds, both models accessed through the @vlmrun Gateway. Let me know what you think! The analysis code is open-source on GitHub: github.com/jeremyipark/visio…

people are in serious denial yes there’s still some code humans are better at but that human is probably not you. also you’re there for @dhh what’d you expect business as usual?

night bike ride vancouver

everything will have models in them we can already run gemma class models on the esp32

i have reported this issue to google before saw it on vertex with gemini 3.5 flash when using structured objects and funcrion calling in the api

they don’t know we’re about to enter the absolute horizon of the attention singularity.

i love these freakin models they make my life so much better. we must accelerate to the maxxx

night bike ride vancouver

i’m very excited by the new jev model, i’ve always believed a faster model is a smarter model

async RL is just horizontal scaling with sticky routing

try riding arbutus all the way up to richmond at night, very strong japan vibes

Work like o3 suggests that future foundation models will diverge like RISC and CISC architectures. Developers will express their system specifications in extremely high-level programming languages. And compilers will translate those into a few RISC—or many CISC—instructions.