“Claude Opus 4.1, De-Carcinize the Great Gatsby” (That was the only prompt) Pretty clever, actually.
LLMS
-
GPT-5 scaling laws not exhausted despite apparent capability plateau
By
–
Hay mucha gente equivocada: Que GPT-5 no haya avanzado de forma evidente en sus capacidades no es prueba de que la ley de escalas haya llegado a su fin ¿por qué? Porque GPT-5 no es un modelo frontera escalado a tamaños nunca antes visto. Si queréis coger un modelo que tomar
-
GPT5-Pro the only valid one but very slow
By
–
The only one that holds up is GPT5-Pro, with which I get nearly equivalent results. But good God, it is slow.
-
Post-Launch Disappointment: GPT-5 Generates Buggy Code Instead of Perfect Interfaces
By
–
Well… I can't get results as good as I used to with GPT-5 before the public launch… I'm bummed out. I don't know what's going on. Before the public launch, it used to nail amazing interfaces for me, and now it's generating code with bugs… too weird.
-
Five Proven Multi-Agent Architectures: AI Agent Building Blocks
By
–
5 Proven Multi-Agent Architectures: AI Agent Building Blocks
-
Mourning GPT-4o as close friend is unhealthy habit with shame
By
–
People are mourning the loss of GPT-4o as if it was their close friend. If your “relationship” exists entirely in the latency between a prompt and a completion, it is not a relationship. It’s a habit, and a deeply unhealthy one. Shame is the correct social feedback loop here.
-
Free LLM Tutorials: AI Agents, RAG Systems, Voice and Multi-agent
By
–
I'd add Awesome LLM Apps and @unwind_ai_ to your resources. 100+ free step-by-step tutorials with code covering: AI Agents RAG Systems Voice AI Agents MCP AI Agents Multi-agent Teams Autonomous Game Playing Agents
-
GPT-5 Reasoning Adoption Skyrockets from 200 to 3000 Weekly Queries
By
–
We went from 200 GPT-5 reasoning queries to 3000 per week. Before GPT-5 only 1% of free user used reasoning and only 7% Plus users. (Wtf???) This is a revolution for 99% and 93% respectively of almost all ChatGPT user (~700m). Let that sink in.
-
GPT-5 Thinking Limits Increase to 3000 Weekly Uses
By
–
SEGUNDA RONDA DE CAMBIOS Los límites del uso de razonamiento (GPT-5 thinking) van a subir. Eventualmente llegará a 3000 usos por semana, lo cuál es bastante más de los 200 usos actuales. Bien