<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Artificial Intelligence on Pasquale Langella</title><link>https://news.pasqualelangella.com/en/categories/artificial-intelligence/</link><description>Recent content in Artificial Intelligence on Pasquale Langella</description><generator>Hugo -- gohugo.io</generator><language>en</language><lastBuildDate>Sat, 22 Feb 2025 10:30:00 +0000</lastBuildDate><atom:link href="https://news.pasqualelangella.com/en/categories/artificial-intelligence/index.xml" rel="self" type="application/rss+xml"/><item><title>How o3-mini-high Solved a Decades-Old Programming Challenge</title><link>https://news.pasqualelangella.com/en/2025/02/22/how-o3-mini-high-solved-a-decades-old-programming-challenge/</link><pubDate>Sat, 22 Feb 2025 10:30:00 +0000</pubDate><guid>https://news.pasqualelangella.com/en/2025/02/22/how-o3-mini-high-solved-a-decades-old-programming-challenge/</guid><description>Since 2023, I have been experimenting with solving the 227 Puzzle challenge hosted on the online judge platform using OpenAI’s GPT models. After countless trials, chatGPT cracked it when the o3-mini-high model was released in February.
Why was this puzzle so challenging? The 227 Puzzle, a decades-old brain teaser, involves sliding tiles into place — deceptively simple yet complex to solve programmatically.
The online judge platform hosts programming challenges that help users prepare for competitive programming contests.</description></item><item><title>Building an Auto-Brightness Script with ChatGPT</title><link>https://news.pasqualelangella.com/en/2025/02/14/building-an-auto-brightness-script-with-chatGPT/</link><pubDate>Fri, 14 Feb 2025 10:30:00 +0000</pubDate><guid>https://news.pasqualelangella.com/en/2025/02/14/building-an-auto-brightness-script-with-chatGPT/</guid><description>Ever get tired of constantly adjusting your screen brightness depending on the lighting in your room? I did too. So, I had an idea: why not automate it? But instead of spending hours researching APIs and troubleshooting errors alone, I teamed up with ChatGPT to help me build a script that would do it all for me.
What started as a simple question—&amp;ldquo;how can I change the screen brightness in windows 11 using python and winsdk?</description></item><item><title>Architectural Kata Agile Dead Trees Solution By GPT-4o</title><link>https://news.pasqualelangella.com/en/2024/06/14/architectural-kata-agile-dead-trees-solution-by-GPT-4o/</link><pubDate>Fri, 14 Jun 2024 10:30:00 +0000</pubDate><guid>https://news.pasqualelangella.com/en/2024/06/14/architectural-kata-agile-dead-trees-solution-by-GPT-4o/</guid><description>One year later the experiment about creating a solution for the Architectural Kata Agile Dead Trees using chatGpt that you can find here
I asked the same questions to GPT-4o and the results are quite impressive. At the end of the article I&amp;rsquo;m explicitly asking to create the software architecture taking into account microservices architecture design patterns, guess how it went :D
This article was featured also on the Dear Architects Mailing list #191</description></item><item><title>Architectural Kata Agile Dead Trees Solution By ChatGpt</title><link>https://news.pasqualelangella.com/en/2023/05/09/architectural-kata-agile-dead-trees-solution-by-chatgpt/</link><pubDate>Wed, 10 May 2023 08:30:00 +0000</pubDate><guid>https://news.pasqualelangella.com/en/2023/05/09/architectural-kata-agile-dead-trees-solution-by-chatgpt/</guid><description>This is an experiment to check the ability of ChatGPT (GPT-4) to create software artifacts from given requirements. The architectural kata is taken from Ted Neward&amp;rsquo;s repository tedneward/ArchKatas. The ChatGPT output was taken as it was generated without any modification, even the text formatting was generated in markdown language and left as it was generated. I will try to score the tasks from 0 to 10 considering how useful and precise is the generated output.</description></item><item><title>Artificial Intelligence in Software Development</title><link>https://news.pasqualelangella.com/en/2023/05/08/artificial-Intelligence-in-software-development/</link><pubDate>Mon, 08 May 2023 10:30:00 +0000</pubDate><guid>https://news.pasqualelangella.com/en/2023/05/08/artificial-Intelligence-in-software-development/</guid><description>Artificial intelligence (AI) is the ability of machines to perform tasks that normally require human intelligence, such as reasoning, learning, decision making, and creativity. AI has been advancing rapidly in recent years, thanks to the availability of large amounts of data, powerful computing resources, and breakthroughs in algorithms and techniques.
One of the domains where AI can have a significant impact is software development. Software development is the process of creating, testing, deploying, and maintaining software applications that run on various devices and platforms.</description></item><item><title>How computers learn</title><link>https://news.pasqualelangella.com/en/2020/03/06/how-computers-learn/</link><pubDate>Fri, 06 Mar 2020 08:49:58 +0000</pubDate><guid>https://news.pasqualelangella.com/en/2020/03/06/how-computers-learn/</guid><description>This article is intended for non-experts who want to have a basic understanding of how Artificial Intelligence works.
All the programs we run on our computers are made up of algorithms. An algorithm is a sequence of instructions that the computer executes to accomplish a specific task. From simpler tasks such as additions to more complex ones such as learning algorithms.
Some history Learning algorithms are based on mathematical methodologies that have been developed since 1935 within a branch of applied mathematics called operational research.</description></item></channel></rss>