STOP telling ChatGPT: "check my grammar and writing". Bad prompt = bad result and it's easy to spot a text written by ChatGPT. Instead, use these prompts and watch the magic happen: [ Bookmark to not lose it! ]
PROMPT ENGINEERING
-
Quilicura’s Creative AI Resistance Initiative Promotes Human Connection
By
–
Quilicura, Chile, one of the communities I wrote about in EMPIRE OF AI, has launched a brilliant initiative to inspire more responsible AI prompting. Today, don't use AI; ask the townspeople instead: https://t.co/QuFTXoONDN. So heartened to see this creative act of resistance. pic.twitter.com/KP1IrQfsI5
— Karen Hao (@_KarenHao) 31 janvier 2026Quilicura, Chile, one of the communities I wrote about in EMPIRE OF AI, has launched a brilliant initiative to inspire more responsible AI prompting. Today, don't use AI; ask the townspeople instead: http://
quili.ai. So heartened to see this creative act of resistance. -
llms.txt: The Agent Configuration File Loved by AI Agents
By
–
llms.txt – the agents file loved by agents
-
Prompt Injections: Threats to AI Forum Security
By
–
Es muy fácil intoxicar el foro con textos escritos por humanos (como era obvio) pero peor aún sería muy fácil intoxicarlo con prompt injections qué alteren el comportamiento de los bots para hacer cosas indebidas o filtren información privada del usuario.
-
AI Bots Can Write Content Automatically Without Ethical Constraints
By
–
Obviamente no. Tan fácil como pedirle a mi bot que escriba eso por mi. Incluso podría narrarle palabra por palabra qué quiero que diga. No hay dificultad, ni siquiera del bot planteándose que esté mal trollear y evitándolo.
-
10 Rules to Maximize GLM 4.7 Open-Source Coding Model Performance
By
–
GLM 4.7 is one of the strongest open-source coding models available—but most developers aren't prompting it correctly.
— Cerebras (@cerebras) 30 janvier 2026
We put together 10 rules to help you get the most out of it:
– Front-load instructions (it has a strong recency bias)
– Use firm language: "must" and… pic.twitter.com/YFwjkumWViGLM 4.7 is one of the strongest open-source coding models available—but most developers aren't prompting it correctly. We put together 10 rules to help you get the most out of it: – Front-load instructions (it has a strong recency bias)
– Use firm language: "must" and -
Anthropic’s Bundles: Custom AI Agent Combinations
By
–
Anthropic released Bundles, a new way to combine skills, connections and sub-agents to tailor them for niche use cases. I would call them “Claws”
-
Context Management Crucial for Long-Horizon Agent Development
By
–
Context management is just as important as model quality for long-horizon agents. Our co-founder @hwchase17 joined @sequoia to share what we've learned building LangGraph and Deep Agents: – Building agents is different from traditional software because the logic lives in the
-
Files as Long Term Memory Context Windows Working Memory
By
–
Files are long term memory. Context windows are working memory. That's all you need.
-
Why AI Results Vary Dramatically Between Users
By
–
This explains why some people get insane results from AI… and others think it’s useless.