Codedgar
3.7K posts
Codedgar
@codedgar_dev
Frontend Design Engineer · DX-focused Design systems, performance & frontend architecture · Tech Lead ▄▀▄▀▄▀▄▀▄▀▄▀▄▀▄▀▄▀▄▀▄▀▄▀▄▀▄▀▄▀▄ Tinkerer, maker
Ciudad Autónoma de Buenos Aire Joined Haziran 2019
262 Following512 Followers
Así me siento cuando uso claude para centrar un div
Español
@santtiagom_ el acercamiento, el taste y el workflow. La IA solo ejecuta, es uno quien decide, planea y pone los requerimientos
Español
Alguien me puede explicar
¿¿QUÉ ESTÁ PASANDO EN BRASIL??
Ayer lo de la muchacha en São Paulo y hoy lo de Oliver Tree en Rio de Janeiro.
CNN Brasil@CNNBrasil
Cantor Oliver Tree é um dos mortos em acidente aéreo no Rio; veja vítimas cnnbr.app/short/c3070580…
Español
Español
@P_Polci amigo esto es lo mejor del mundo jajajaja
Codedgar@codedgar_dev
ESTO FUNCIONA BWAHAHAHAHAHA
Español
@P_Polci meparece que voy a empezar a usar al asistente de mp como si fuera chatgpt y todos deberian hacer lo mismo hasta que vean el gasto que esto conlleva y devuelvan las opciones que quitaron para dárselas al asistente
Español
@ALASKANmagpie iphone user here!
controls feel good but if it had vibration as feedback it would be better, also orbiting side to side felt like it was inverted to me, and the A button suddenly stopped working
English
Android user here.
I want to make sure iphone gesture controls well on Fableboy.shinythings.space
Got an iphone?
If you read this, and care to test it for me, please drop how it handles below!
I'll send you early access to the other consoles :D
#iphone #test #indiedev
English
@iiiipotatoes @DRIVECLUB_GAME you’re confusing visual style with gameplay mechanics
English
@DRIVECLUB_GAME Forza is a racing game not a sim. Giving a shit about top of the line rain physics in forza totally misses the point.
English
@ziwenxu_ @entrynumber1 i’ll take a look and let you know if ur cooking
English
@codedgar_dev @entrynumber1 Try it and let me know the benchmarks is there as well
x.com/ziwenxu_/statu…
Ziwen@ziwenxu_
We are finally getting our fable back. I built a repo that runs two opus 4.8 on the same question in parallel, blind to each other base on the OpenRouter Fusion. Then a third opus reads both and writes the final answer from where they agree, where they split, and what they both missed. One run can be confidently wrong. Two, cross-examined, can't hide it. Put the real fable system prompt on top of the claude.md and the judgment comes back. It sounds like fable again because it's doing what fable did. Link's in the comments.
English
WE ARE SOOOOO BACK!
Someone leaked the Claude Fable 5 system prompt and ran it on an Opus 4.8
Output is like 90% of the real thing
Turns out half the magic was never the weights. It was the prompt the whole time
Repo down below:
Jamieson O'Reilly@theonejvo
Did I just unlock claude-fable-5-lite? 😂 Since Fable 5 got pulled (US export control order, Anthropic is contesting it), I wanted to see how much of its character lives in the system prompt vs. the model itself. I ran the leaked Fable 5 prompt on Opus 4.8 head-to-head against stock 4.8.
English
@ziwenxu_ @entrynumber1 Don’t get me wrong, i’m super excited to be proved wrong. Are the benchmarks similar or is it just “try it”?
English
@codedgar_dev @entrynumber1 Check out the fusion from open router made + this fable system prompt
You guys should know we have something back 🤣
English
@entrynumber1 @ziwenxu_ i can ask a cat to act like a puma but it won’t make it one lmao
plus, no benchmarks? all cap
GIF
English
@gonzamartinese y esto va a ser para un cliente o sale librería? 👀
Español
@buildwithsid most of their distribution is done on other media like social media, ads and so on, the page tends to be mainly utilitarian
English
