The prompt engineering fashion is over. Now what is important is loop engineering

In the last three years we have seen how if you wanted to be an advanced user of AI, you had to become a prompt engineer: The way you ask the AI ​​things was vital to achieving the best results. That idea is now becoming obsolete, because an even more promising technique is beginning to emerge to make the most of chatbos. From prompts to loops. The new paradigm that has become a viral trend among developers is that of the so-called “loop engineering” (“loop engineering”) that assumes something important: that the AI ​​is going to hallucinate or make mistakes. And with this method a feedback system is implemented: a subagent generates a response, another audits it and looks for errors, and then the system automatically reruns the process until the result meets the quality standards specified by the user. AI Gurus Recommend Loops. Boris Cherny, creator of Claude Code, explained in a recent talk how he no longer writes prompts in Claude Code, but instead writes loops. “Loops do the job. My job is to write loops.” Peter Steinberger, creator of OpenClaw, agreed and commented on X that “you should not write prompts for scheduling agents. You should design loops that create prompts for your agents.” Addy Osmani, head of Google Cloud, exactly stated same idea: “loop engineering is replacing you as the person who creates the prompts for the agent. You design the system that does that instead of you.” Implacable cycle. This type of approach is what has managed to succeed in AI agents such as Claude Code or OpenClaw. The model can run code in a safe environment, test it, read error messages if they exist, and then fix those failures to get back to the beginning. AI already “reasoned”, but now it is capable of self-assessment and self-correction autonomously and independently. Steinberger put a clear example how to design one of these loops. Goodbye to the chat window. The technique is being very popular among developers, but at the same time it poses a potential disappearance of the traditional chatbot in the browser window. The value was previously in chat with AI and experiment with promptsbut now the idea is to propose automated workflows. The user only sees the initial problem and the final solution, there are no constant questions and doubts unless the user wants to refine after that final solution. Be careful with costs. The problem with this idea is that by designing a loop one can launch several subagents that work in parallel. This implies an expenditure of tokens that can be considerable, which threatens to be very expensive. The recommendation, of course, is to use subagents and loops when it makes sense. Another stage in the evolution of AI. The passing of the prompts to loops poses a new phase in the evolution of AI. ChatGPT amazed us by creating quick poems, but the process was inefficient because talking is not always the optimal route to achieve the desired result. The profession of ‘prompt engineer’ could therefore be threatened after that initial phase in which knowing how to talk to the AI ​​was the important thing. Now the powerful thing is knowing how to design those loops that end up doing everything for the user. Image | Compagnons In Xataka | Claude Code is being the big favorite among programmers. So much so that he already signs 4% of everything that is uploaded to GitHub

Loop Infinito, Xataka’s daily podcast, will record live in Seville on March 19: this is how you can come

The next March 19, Infinite Loop leaves the usual studio. Within the framework of CTx Techthe great technology event that It is celebrated in Seville on the 19th and 20thI will record a special live episode with Antonio Ortizone of the founders of Xataka and current podcast co-host Stochastic Monkeys. It will be at 8:40 p.m. at the ADA Auditorium. The topic: AI without hype. What is real, what is noise and why it is so difficult to distinguish one from the other. If you are going to be in Seville those days – or if the event itself is reason enough to come – we will be there. CTx Tech brings together more than 400 hours of content and 15,000 expected attendees. Tickets are available at ctx-tech.com. Featured image | Transfers

Welcome to Loop Infinito, Xataka’s daily podcast about technology

Infinite Loop changes house and focus. After six years as a daily podcast Applesphere focused on Apple, now move on to Xataka and expands its focus to technology in general. The format does not change: it is still a daily episode of analysis and technological context, published Monday to Friday at 7:00 a.m. (Spanish peninsular time). What changes is the thematic scope: Apple will continue to be common, but it will no longer be the only protagonist. What is Infinite Loop. It is a technological analysis podcast presented by yours truly, Javier Lacort. Each episode addresses a relevant topic: business decisions, product trends, technological geopolitics. The focus is on the context, not the news: what it means, why it matters, how it fits. Without hypewithout jeers, without noise. For six years I have applied that view to the Apple ecosystem. Now I apply it to the entire technology industry. The first two episodes of this stage: Why this change?. Technology doesn’t happen in silos. Apple does not exist in isolation from Google, Microsoft, chipmakers, Chinese regulations, or European Union decisions on AI. To really understand what is happening, a broader vision is needed. Loop Infinito had already explored topics beyond Apple. Now that movement is formalized: the podcast goes from Applesphere to Xataka and is completely open to any relevant technological topic. What changes for today’s listeners. Nothing in practice. He feed of the podcast does not change, there is no need to resubscribe. The format, duration, tone and structure remain identical. Just change the cover (from purple to black background) and the letterhead. Some technical adjustments will arrive in the next few days, but they will be invisible to the listener. What it means for Xataka readers. Loop Infinito is now part of the Xataka content ecosystem. A daily audio format that complements written analysis with a technology context piece each morning. If you are looking to follow current technological news clearly and without noise, Loop Infinito is available on all the usual podcast platforms: Featured image | Xataka with Mockuuups Studio In Xataka | I increasingly like technology that doesn’t want anything from me: the one that has a purpose and leaves you alone

Your mind can activate a loop song without asking you permission. Science knows why he does it … and why he doesn’t know how to stop

You are silent. Walking down the street, serving a coffee, looking distracted by the mobile. And suddenly … there is again. A melody you have not chosenbut who insists on returning. As a drop in the tap, as a notification that you cannot deactivate. In my case, it is the same song for a couple of days. Always the same part, as if the rest did not exist. It does not bother me, but it has made me think: why does this happen? Does our brain make sense, sometimes it works like a striped disk? What is exactly an Earworm. The Earworms – Also called “ear worms” – they are musical fragments that are installed in the head and repeat themselves again and again, without you chosen. The term comes from German Ohrwurm And today describes a mental phenomenon as recognizable as elusive. It is not something weird: As the National Medicine Library of the United States collectsup to 98% of the western population has ever experienced them. Most live them as a simple anecdotebut for some people they can become annoying or even distressing. We speak in a very specific way of spontaneous mental activity that science has been trying to understand. Why do some songs stuck. Earworms are the result of a combination of musical and neurological factors. The themes that are most repeated usually have simple structures, fast tempos and easy to hum melodies. This was revealed by a study led by musicologist Kelly Jakubowskiwhich analyzed more than 3,000 songs and found that those who stayed in their heads tended to have common melodic contours and a medium tempo faster than the rest. Among the most mentioned songs such as Earworms in Jakubowski’s study and his team, several Anglo -Saxon pop hits stand out. It is no accident: the work was done in the United Kingdom with English -speaking participants, so most of the topics that appear are in English. Even so, many of them have been true global successes, also known by the Spanish public: ‘Bad Romance’ – Lady Gaga ‘Can’t get you out of my head’ – Kylie Minogue ‘Don’s Stop Believin’ ‘ – Journey ‘Hoilebody That I used to know’ – Gotye ‘Moves Like Jagger’ – Maroon 5 ‘California Gurls’ – Katy Perry ‘Bohemian Rhapsody’ – Queen ‘Alejandro’ – Lady Gaga ‘Poker Face’ – Lady Gaga The decisive occurs in the brain: the auditory cortex – the same one we use to listen to real music – is reactivated even when we simply imagine a song. The emotional state also influences: stress, distraction or nostalgia can open the door for a melody to be installed without prior notice. Auditory cortex Some minds are more prone to loop. Not everyone lives the Earworms the same. Some people barely notice them, while others suffer with intensity, as if the brain stayed in a loop. In most cases, Earworms are lived as a simple curiosity or even as something entertaining. But when the repetition becomes persistent and annoying, it can be a sign of something more serious. According to psychiatrist Srini PillayProfessor at Harvard’s Faculty, “these persistent loops can be associated with obsessive-compulsive disorders, migraines, unusual epilepsies, palinacousis, stroke or cerebral metastases.” It is not usual, but it can happen. What to do if you don’t want to keep listening to her. There is no magic formula to eliminate an EARWORM, but there are strategies that help. Curiously, try to block the song It is the least effective: the more struggles against her, the more she clings, a phenomenon described by Daniel Wegner as “ironic process.” Instead, accepting it without resistance usually works better. As the Kennedy center collectssome people choose to listen to the complete song; Others replace it with another melody. There are specialists who point to chew gum To interfere mental repetition. And you, what song isn’t you going from your head? Since I started investigating the Earworms, the song in my head has not disappeared. Now I know that I am not the only one, that there are reasons behind and that, deep down, that loop is part of how our brain works. And you? Have you ever had an Earworm that you couldn’t take off from your head? What was that song impossible to erase? Do you have any technique to take it off? We read you in the comments. Images | Xataka with Gemini 2.5 Flash | Amanz | Kennedy Center In Xataka | I put myself in the hands of some “sleep headphones” in the hope of reconciling sleep. It has come out regular

Log In

Forgot password?

Forgot password?

Enter your account data and we will send you a link to reset your password.

Your password reset link appears to be invalid or expired.

Log in

Privacy Policy

Add to Collection

No Collections

Here you'll find all collections you've created before.