i'm launching an open-source Whisperflow
super fast speech to text
it includes smart formatting
"Run the slash go command" 🠮"Run the /go command"
"We need to do the following, first A then B, clear?" 🠮 "We need to do the following:
- First A
- Then B
Clear?"
repo below
Lo más importante de la salida de Fable / Mythos es la demostración, una vez más, de que no hay muro. El paradigma de los LLMs y el test-time-compute lejos de frenarse sigue trepando la colina trayendo modelos cada vez más inteligentes y capaces, que están transformando el mundo.
Da igual los análisis coyunturales de qué lab se pone por encima, a qué coste, cuánto es subvencionado, o con qué limitaciones.
Nada de esto es tan importante como que la humanidad sigue encontrando rendimientos de una tecnología que cada vez nos aporta más inteligencia en la resolución de problemas cada vez más complejos. La frontera se sigue moviendo y el muro nunca existió.
Fable 5 is state-of-the-art on nearly all tested benchmarks, with exceptional performance in software engineering, knowledge work, scientific research, and vision.
The longer and more complex the task, the larger Fable 5’s lead over our other models.
inspired by this conversation I built a text replacement system
took Pietro's replacements and added some of my own
repo of it + linux setup in the tweet below
"Coding agents are eating software" @skirano
(ex-Anthropic)
Pietro Schirano reveals the Codex setup that 10x'd his speed, text commands, multi-agent spawning, agent-first design
He even built a game for a Flipper Zero with one prompt
Here is the full episode:
opus 4.8 is like talking to a french philosophy student that will cirtique your thought process
gpt5.5 is like talking to some dirty garage mechanic that gets shit done
Lmux had some lag, feels bad to use
just asked Codex /goal to use Lmux, measure lag / stutter and reduce it
"keep working until it is perfect no lag" genius 200 IQ prompting