@Chica_de_prensa

Thread

Anoche hubo una "batalla campal" en el Congreso por una oficina. Una fuente de Ahora Nación me contó los entretelones de lo que pasó. Abro hilo 🧵👇🏼...

@alex_prompter

Article

Stop rewriting your prompts. Start answering the model's questions....

@Mr_gomatiprasad

Thread

🚨 BREAKING: NotebookLM is no longer just a PDF summarizer. It can now help turn a messy research idea into a structured research system, analyze data, and create outputs like reports, charts, spreadsheets and slide decks. Here’s the workflow most people still aren’t using: ...

@de1lymoon

Article

• A prompt is a request. You send text, you get text back, and the whole transaction is over in one call. ...

@sirbayes

Thread

Predicting the answer to interventional "what if?" questions — the outcome of an action you never took — need a *mechanistic* model, not a curve fit. And you can only learn one by *experimenting*. Experiments are costly, so the real game is **data efficiency**. Meet the Model Discovery Agent (MDA)....

@carm1nee

Article

There is a lot of investing advice written by people who have never lost money at scale....

@0xRicker

Article

A pile of 300 answers is not knowledge. Kimi Agent Swarm doesn't just run agents in parallel. It wires what they find into a single connected graph you can actually use....

@andreysuperior

Article

You are using one of them right now. Probably the worst one. And nobody has ever told you that the other three exist because the people who use them do not write blog posts. They are too busy compounding....

@LiveLawIndia

Thread

#BREAKING Calcutta High Court hearing a plea challenging the WB Govt’s order to remove #loudspeakers from #Mosques and other religious places. Sr Adv Kalyan Bandopadhyay: They have removed loudspeaker used for Azaan from 4000 mosques. No written order will be served, but police implement it. This ...