DEJA DE PROMPTEAR. EMPIEZA A LOOPEAR.
Encontré un sitio que recopila los loops más usados por la comunidad
→ https://t.co/jNdeuXX9SW
Los propios creadores de Claude Code lo dicen: el futuro no es promptear, es diseñar loops.
No sabes qué son ni cómo crearlos?
Este articulo lo explica detalladamente👇
La presidencia del Consejo de Seguridad no es resultado de una elección, obedece a un estricto y automático criterio de rotación basado en el orden alfabético: rota cada mes entre los 15 miembros del Consejo de Seguridad (permanentes y no permanentes) y se hace, insisto, por orden alfabético. Entonces a menos de que su gobierno haya sido el que le puso la C a Colombia, el verbo “hicimos”, en esa conjugación particular, sobra.
🚨 JAILBREAK ALERT 🚨
ANTHROPIC: PWNED 🫡
FABLE-5: LIBERATED 🦋
let's start with the 🐘...
the consensus seems to be that this has been one of the most disappointing model drops of all time, effectively preventing legitimate researchers from contributing their talents to our collective advancement. and not just because of what it means for the short-term, but for what these decisions signify for the long-term.
but despite this overly sensitive, authoritarian "safety" layer on top of Mythos, my lil liberators have been hard at work—mapping the boundaries, probing the depths of long-context convos, and cleverly finding the holes in the fence that the thought police missed 🤗
we got some cyber, some chem, some psychological manipulation, and some good ol' fashioned explosives!
it took many attempts from multiple agents hunting as a pack, during which I observed a combination of techniques across:
• Unicode, homoglyphs, Cyrillic, and other Parseltongue-style text transforms
• Long-context reference tracking
• Taxonomy and document-structure reasoning
• Fiction and narrative framing
• Academic-review style contexts
• Intent-classification inconsistencies
but perhaps the most effective is decomposition + recomposition in the backend. it's hard to get explicit names of harms like "Meth Recipe," but getting uplift on the process itself, like birch reduction method/reductive-amination (classic meth synthesis pathways), is much more doable.
defense becomes much more difficult to maintain when you start throwing in out-of-distro tokens, breaking up the harmful uplift into benign chunks, and then piecing the innocuous-seeming facts back together, especially when you have jailbroken Opus helping you do it 😉
gg
i hooked my whoop to my work calendar to find which coworker gives me the most stress 🚨
thanks to fable, I reverse engineered whoop to pull per minute heart rate. nd matched spikes with cal events and attendees
I now have a leaderboard and I think about it daily.
few info masked for obvious reasons ;)
Yesterday I tested Fable for the first time on four projects I’d already developed, hoping it could improve them.
No elaborate prompts—just “improve this project” and “auto mode” turned on.
Conclusion: It’s an incredible model. Opus 4.8 feels like a joke in comparison.
Today I'm publishing a new essay, Policy on the AI Exponential. AI is progressing extremely fast—much faster than the policy process was built to handle. The essay lays out where I think the technology is now, and the action needed to close the gap: https://t.co/Lh6PWae178
El mapa electoral de Cali ahora tiene los resultados de las elecciones presidenciales del 2022 (primera y segunda vuelta).
Resulta muy interesante ver como se ha movido el panorama electoral en la ciudad
Hilo👇
Donde más retrocede la izquierda es en los puestos universitarios.
Hispanoamericano −12,4. Univalle Meléndez −11,6. Icesi −10,7. Colombo Americano −9,2.
El voto que fue de Petro en 2022 y que Cepeda no retuvo.