lo peor de esto es que si en lugar de ponerlo al principio lo ponian al final seguro todos los bancaban por sponsorear tremendo show, como cambia tener a alguien que piense en el sector de marketing eh
I actually can't believe how good LLMs have gotten. been searching for a specific app that I needed that I couldn't find for a few days, told codex to make it and it was done 20 minutes later. actually crazy.
I have been using opus 5.5 all morning and used only 3% of my weekly usage ($200 max plan) this thing is insane 😭😭
is Fable 5.1 better than Opus 5.5 in planning at least? if not I think I will just use opus 5.5 for planning as well as implementing
que completa barbaridad de modelo
Check out side-by-side outputs generated on Arena from Claude Opus 5.5 by @AnthropicAI and GPT-6 Sol by @OpenAI.
Scores for @claudeai Opus 5.5 are coming soon. Real-world tasks from our global community of users power the Arena leaderboards. Head to Arena now to test it out, and stay tuned!
for every 100 lines of code an agent generates 1000 lines of unit tests are written, are unit tests even worth it anymore?
holy shit it works
New blog post:
We had a million lines of Python to clean up. On September 2nd @Teknium asked Hermes Agent to do it.
1,393 subagents and nineteen hours later, the codebase was 34.4% smaller, saving us nearly $2m in engineering hours.
nousresearch.com/refactoring…
this guy is a generational talent, elon level
Omarchy now has the coolest website I've ever seen. Truly incredible work by the Omarchy website design team lead by @BarisGirismen. This is what computers can look (and sound) like! omarchy.org
