@steipete Its applicable not only to skills, but to anything you put in context - i made a small util to estmate token cost:
https://t.co/r2B8J4pFD1
In some cases, we had specs and skill catalogs spannning up to millions of tokens :)
I can't stop playing with Rapid Roboflow.
The process is so smooth that you can just:
- Go to the rapid roboflow platform
- Drop a few images or a short video
- Type a prompt like “yellow cap” or “person wearing red hat”
- Instantly get a working detection model
No training, no GPUs, no cloud setup. Plug it straight into your app.
It’s also baked into Roboflow Workflows, so you can instantly build automations like “count vials crossing this line” in minutes.
Computer vision just went from weeks in seconds.
This is quite massive
Mistral has just released two open-source models including 'Devstral Small 2' which:
- Has only 24B parameters (28x smaller than DeepSeek 🤯)
- Can run LOCALLY on a laptop
- Is competitive with much larger models for coding
So basically everything you need for 100% privacy and unlimited vibe coding.
Plus, they're releasing a new vibe coding tool called Mistral Vibe CLI that you can use for free with their bigger model Devstral 2 (123B).
Western open source is so back.
@lexfridman@elonmusk Given how long it will take - trillions of trillions of years - probably not the first priority problem :)
https://t.co/5GPrJV90UD
@richard_littler Add the other two parts to Neuromancer - Count Zero and Mona Liza Overdrive...
Also Lucifers Hammer by Larry Niven
The Futurological Congress by Stanislaw Lem
NEW § @BrandonByars: we should prefer general purpose languages for integration: they manage the complexity of evolving interfaces and prevent implementation leaking into those interfaces
https://t.co/DIUENi6bg5