| ÚLTIMA HORA: Claude ahora puede investigar como un estudiante de doctorado de Stanford. Aquí os dejo los 9 mejores e infalibles prompts de Claude que convierten más de 40 artículos de investigación en revisiones de literatura estructuradas, mapas de conocimiento y lagunas de
LLMS
-
Gemini Excels in Benchmarks, Becoming Top AI for Code
By
–
The ACM Turing Award will be announced tomorrow. Any guesses on who won it?
-

Composer Uses RL Self-Summarization to Cut Compaction Error 50%
By
–
We trained Composer to self-summarize through RL instead of a prompt. This reduces the error from compaction by 50% and allows Composer to succeed on challenging coding tasks requiring hundreds of actions.
-
Building Reliable Agents for Production Deployment
By
–
💫 New LangChain Academy Course: Building Reliable Agents 💫
— LangChain (@LangChain) 17 mars 2026
Shipping agents to production is hard. Traditional software is deterministic – when something breaks, you check the logs and fix the code. But agents rely on non-deterministic models.
Add multi-step reasoning, tool… pic.twitter.com/fWt2UhHQEbNew LangChain Academy Course: Building Reliable Agents Shipping agents to production is hard. Traditional software is deterministic – when something breaks, you check the logs and fix the code. But agents rely on non-deterministic models. Add multi-step reasoning, tool
-

KARL: Knowledge Agents via Reinforcement Learning Research
By
–
"You can think of this as RAG — but like RAG plus plus plus plus plus plus, all the way up to 200 vector database calls." — @jefrankle
, Chief AI Scientist at Databricks. We published new research on KARL — Knowledge Agents via Reinforcement Learning — a RAG agent trained -

Codex Rate Limited by Excessive Subagent Usage
By
–
lol i got rate limited by codex for using too many subagents
-

5.4 Mini and Nano AI Models Released at Lower Prices
By
–
Ok I was wrong – 5.4 Mini and 5.4 Nano are out. Mini is 1/3 of 5.4 and nano is 1/10 the price
-

OpenAI Releases GPT-5.4 Mini and Nano Models
By
–

BREAKING : OpenAI released GPT-5.4 Mini and GPT-5.4 Nano on the APIs. A mini version is also available on ChatGPT and Codex apps. Check intelligence
-

OpenAI Launches GPT-5.4-Nano and Mini Models on Poe
By
–
OpenAI's GPT-5.4-Nano and GPT-5.4-Mini are now live on Poe. GPT-5.4-Nano is a strong fit for fast, high-volume tasks like summarizing transcripts, labeling tickets, rewriting content, quick RAG answers, and running @openclaw flows with Poe where latency and cost matter most.
