Over the last period I’ve been working on Luminara, a full-featured HTTP client built directly on top of native fetch. 
The idea wasn’t to create “yet another wrapper,” but to build a complete request lifecycle around fetch — something that’s usually spread across multiple small libraries.

The project is open-source here: 
👉 <a href="https://github.com/miller-28/luminara" rel="noopener noreferrer">https://github.com/miller-28/luminara</a>

Live sandbox and documentation: 
👉 <a href="https://luminara.website" rel="noopener noreferrer">https://luminara.website</a>

🟣 npm 
<a href="https://www.npmjs.com/package/luminara" rel="noopener noreferrer">https://www.npmjs.com/package/luminara</a>

<h2>
 
 
 Why I built it
</h2>

In most real-world applications, a simple fetch() isn’t enough. 
You eventually need:

<ul>
<li>Retries</li>
<li>Backoff strategies</li>
<li>Timeout control</li>
<li>Request cancellation</li>
<li>Deduplication</li>
<li>Debouncing</li>
<li>Rate limiting</li>
<li>Interceptors</li>
<li>Logging</li>
<li>Metrics / stats</li>
<li>Error classification</li>
<li>Consistent behavior in browser + Node</li>
</ul>

Developers usually assemble this from several packages, custom utilities, or ad-hoc logic scattered across codebases.

Luminara tries to bring the entire lifecycle into one place — without adding dependencies, and without hiding fetch.

🙌 Looking for Feedback

I’d love to hear from other developers who have built or maintained HTTP layers:

Is the API intuitive?

Any design mistakes or surprising decisions?

Features you’d expect but don’t see?

Anything you'd simplify or reorganize?

Open to critique — architectural, naming, ergonomics, anything.

Luminara هو عميل HTTP شامل تم تطويره على أساس native fetch، بهدف تبسيط دورة حياة الطلبات التي غالبًا ما تتوزع عبر مكتبات متعددة. المشروع مفتوح المصدر ومتوفر على GitHub، مع وجود صندوق رمل مباشر ووثائق مقدمة على موقعه الإلكتروني. تلبي Luminara الاحتياجات الشائعة في التطبيقات الواقعية، مثل إعادة المحاولة، واستراتيجيات التراجع، والتحكم في المهلة، مما يعزز من وظائف واجهة برمجة التطبيقات الأصلية fetch.

Luminara es un cliente HTTP completo desarrollado sobre la base de native fetch, con el objetivo de simplificar el ciclo de vida de las solicitudes que a menudo se fragmenta en varias bibliotecas. El proyecto es de código abierto y está disponible en GitHub, con un sandbox en vivo y documentación proporcionada en su sitio web. Luminara aborda necesidades comunes en aplicaciones del mundo real, como reintentos, estrategias de retroceso y control de tiempo de espera, mejorando así la funcionalidad de la API nativa fetch.

Luminara est un client HTTP complet développé sur la base de native fetch, visant à rationaliser le cycle de vie des requêtes souvent fragmenté à travers diverses bibliothèques. Le projet est open-source et disponible sur GitHub, avec un bac à sable en direct et une documentation fournie sur son site web. Luminara répond à des besoins courants dans les applications réelles, tels que les tentatives, les stratégies de retour en arrière et le contrôle des délais, améliorant ainsi la fonctionnalité de l'API native fetch.

Luminara is a comprehensive HTTP client developed on top of native fetch, aiming to streamline the request lifecycle that is often fragmented across various libraries. The project is open-source and available on GitHub, with a live sandbox and documentation provided on its website. Luminara addresses common needs in real-world applications, such as retries, backoff strategies, and timeout control, thereby enhancing the functionality of the native fetch API.

Luminara — A Full Request-Lifecycle HTTP Client Built on Native Fetch

<A HREF="https://fortune.com/2025/11/19/exclusive-doppel-raises-70-million-series-c-at-more-than-600-million-valuation-to-fight-ai-powered-social-engineering-attacks/"><IMG VSPACE="4" HSPACE="4" BORDER="0" ALIGN="RIGHT" SRC="http://www.techmeme.com/251119/i39.jpg"></A>
<A HREF="http://www.techmeme.com/251119/p39#a251119p39" TITLE="Techmeme permalink"><IMG WIDTH=11 HEIGHT=12 SRC="http://www.techmeme.com/img/pml.png" STYLE="border:none;padding:0;margin:0;"></A> Allie Garfinkle / <A HREF="http://www.fortune.com/">Fortune</A>: 
<A HREF="https://fortune.com/2025/11/19/exclusive-doppel-raises-70-million-series-c-at-more-than-600-million-valuation-to-fight-ai-powered-social-engineering-attacks/">Doppel, which makes an AI social engineering detection service, raised a $70M Series C led by Bessemer at a $600M+ valuation, up from $205M in May</A>&nbsp; &mdash;&nbsp; Senior Finance Reporter And Author Of Term Sheet&nbsp; &mdash;&nbsp; I tried to fool my brother, sort of.&nbsp; &mdash;&nbsp; Next to him and his Pekingese on the couch &hellip;

دوبل، وهي شركة متخصصة في خدمات الكشف عن الهندسة الاجتماعية باستخدام الذكاء الاصطناعي، نجحت في جمع 70 مليون دولار في جولة تمويل من السلسلة C بقيادة بيسمر. وقد زادت هذه الجولة من تقييم الشركة إلى أكثر من 600 مليون دولار، ارتفاعًا من 205 مليون دولار في مايو.

Doppel, una empresa que se especializa en servicios de detección de ingeniería social mediante IA, ha recaudado con éxito 70 millones de dólares en una ronda de financiación Serie C liderada por Bessemer. Esta ronda ha elevado la valoración de la empresa a más de 600 millones de dólares, un aumento significativo desde los 205 millones en mayo.

Doppel, une entreprise spécialisée dans les services de détection d'ingénierie sociale par IA, a levé avec succès 70 millions de dollars lors d'un tour de financement de série C dirigé par Bessemer. Ce tour de financement a porté la valorisation de l'entreprise à plus de 600 millions de dollars, contre 205 millions en mai.

Doppel, a company specializing in AI social engineering detection services, has successfully raised $70 million in a Series C funding round led by Bessemer. This funding round has increased the company's valuation to over $600 million, a significant rise from $205 million in May.

Doppel, which makes an AI social engineering detection service, raised a $70M Series C led by Bessemer at a $600M+ valuation, up from $205M in May (Allie Garfinkle/Fortune)

The service is customized for teachers' needs and includes added security and privacy, a collaborative workspace, and more.

OpenAI expands free educational offerings - here's what ChatGPT for Teachers can do

GPT-5.1-Codex-Max is ready to take on your next massive coding job. Here's what's new.

OpenAI's Codex Max solves one of my biggest AI coding annoyances - and adds dramatically faster performance

The agent offers one-click buying for all your holiday needs and will be free for all US-based users.

Perplexity's AI shopping tool is free for all now, just in time for Black Friday - how to use it

<a href="https://fetch.ai/">Fetch AI</a>, a startup founded and led by former DeepMind founding investor, Humayun Sheikh, <a href="https://www.businesswire.com/news/home/20251119088395/en/Fetch-Combines-Personalized-AI-with-Multi-Agent-Collaboration-to-Handle-Complex-Consumer-Tasks-Launches-Claim-Your-Agent-to-Fight-Brand-Knock-Offs">today announced the release</a> of three interconnected products designed to provide the trust, coordination, and interoperability needed for large-scale AI agent ecosystems. The launch includes <a href="https://asi1.ai/">ASI:One</a>, a personal-AI orchestration platform; <a href="https://business.fetch.ai/">Fetch Business</a>, a verification and discovery portal for brand agents; and <a href="https://agentverse.ai/?sort=relevancy&amp;page=1&amp;recommended=true">Agentverse</a>, an open directory hosting more than two million agents. Together, the system positions Fetch as an infrastructure provider for what it calls the “Agentic Web”—a layer where consumer AIs and brand AIs collaborate to complete tasks instead of merely suggesting them.The company says the tools address a central limitation in current consumer AI: models can provide recommendations but cannot reliably execute multi-step actions that require coordination across businesses. Fetch’s approach centers on enabling agents from different organizations to interoperate securely, using verified identities and shared context to complete end-to-end workflows.“We’re creating the same foundation for agents that Google created for websites,” said Humayun Sheikh, Founder and CEO of Fetch AI, and an early investor in DeepMind, in a press release provided to VentureBeat. “Instead of just finding information, your personal AI coordinates with verified brand agents to get things done.”<h2>Background: Fetch’s Founding and DeepMind Connection </h2>Fetch AI was founded in 2017 by Humayun Sheikh, an entrepreneur whose early investment in DeepMind helped support the company’s commercial development before its acquisition by Google. “I was one of the first five people at DeepMind and its first investor. My check was the first one in,” Sheikh said, reflecting on the period when advanced machine learning research was still largely inaccessible outside major technology companies.His early experience helped shape Fetch’s direction. “Even in 2013, it was clear to me that agentic systems were going to be the ones that worked. That’s where I focused—on the agentic web,” Sheikh noted. Fetch built on this thesis by developing infrastructure for autonomous software agents, focusing on verifiable identity, secure data exchange, and multi-agent coordination. Over the past several years, the company has expanded to a 70-person team across Cambridge and Menlo Park, raised approximately $60 million, and accumulated more than one million users interacting with its model—data that informed the design of the newly launched products.Sheikh added that his decision to bootstrap the company initially came directly from the proceeds of the DeepMind exit, noting in the interview that while the sale to Google was “a good exit,” he believed the team could have held out for a higher valuation. The early self-funding period allowed Fetch to begin work in 2015—well before transformer architectures went mainstream—on the hypothesis that agentic infrastructure would become foundational to applied AI.<h2>ASI:One — A Platform for Multi-Agent Orchestration</h2>At the core of the launch is ASI:One, a language model interface designed specifically for coordinating multiple agents rather than addressing isolated queries. Fetch describes it as an “intelligence layer” that handles context sharing, task routing, and preference modeling.The system stores user-level signals such as favored airlines, dietary constraints, budget ranges, loyalty program identifiers, and calendar availability. When a user requests a complex task—such as planning a trip with flights, hotels, and restaurant reservations—ASI:One retrieves those preferences and delegates work to the appropriate verified agents. The agents then return actionable outputs, including inventory and booking options, rather than generic recommendations.In practice, ASI:One functions as a workflow generator across organizational boundaries. By contrast with conventional LLM applications, which often rely on APIs or RAG techniques to surface information, ASI:One is built to coordinate autonomous agents that can complete transactions. Fetch notes that personalization improves over time as the model accumulates structured preference data.Sheikh emphasized the distinction between orchestrated execution and traditional AI output. “This isn’t searching for options separately and hoping they work together,” he said. “It’s orchestration.” He added that Fetch’s architecture is intentionally modular: “Our architecture is a mix of agentic and expert models. One large model isn’t enough—you need specialists. That’s why we built ASI1, tuned specifically for agentic systems.”The interview also revealed new details about ASI:One’s personalization systems: the platform uses multiple user-owned knowledge graphs to store preferences, travel history, social connections, and contextual constraints. These knowledge graphs are siloed per user and not co-mingled with any Fetch-operated data. Sheikh described this as a “deterministic backbone” that gives the personal AI a stable memory layer beyond the probabilistic output of a single large model.ASI:One launches in Beta today, with a broader release planned for early 2026. Fetch also offers ASI:One Mobile, released earlier this year, giving users access to the same agent-orchestration capabilities on iOS and Android. The mobile app connects directly to Agentverse and the user’s knowledge graphs, enabling on-the-go task execution and real-time interaction with registered agents.<h2>Fetch Business — Verified Identity and Brand Control</h2>To enable reliable coordination between consumers and companies, Fetch is introducing a verification and discovery portal called Fetch Business. The platform allows organizations to verify their identity and claim an official Brand Agent handle—for example, @Hilton or @Nike—regardless of which tools they use to build the underlying agent.Fetch positions the product as an analogue to ICANN domain registration and SSL certificate systems for websites. Verified status is intended to protect consumers from interacting with counterfeit or untrusted agents, a problem the company describes as a major barrier to widespread agent adoption.The system includes low-code tools for small businesses to create agents in a few steps and connect real-time APIs such as inventory, booking systems, or CRM platforms. “With Fetch, you can create an agent in one minute. It gets a handle, like a Twitter username, and you can personalize it completely—even give it your social media permissions to post on your behalf,” Sheikh said. Once a brand claims its namespace, its agent becomes discoverable to consumer AIs and other agents inside Agentverse.The company has pre-reserved thousands of brand namespaces in anticipation of demand. Verification status persists across any platform that integrates with Agentverse, creating a portable identity layer for business agents.The interview highlighted that Fetch Business inherits web-trust primitives directly: domain owners verify their identity by inserting a short code snippet into their existing website backend, allowing the system to pass a cryptographic challenge and grant the agent an authenticity badge similar to a “blue check” for agent identities. Sheikh framed this as “reusing the trust layer the web already spent decades building.”Companies can begin claiming agents now at <a href="https://business.fetch.ai/">business.fetch.ai</a>.<h2>Agentverse — An Open Directory of More Than Two Million Agents</h2>The final component of the release is <a href="https://agentverse.ai/">Agentverse</a>, an open directory and cloud platform that hosts agents and enables cross-ecosystem discoverability. Fetch states that millions of agents have already registered, spanning travel, retail, entertainment, food service, and enterprise categories.Agentverse provides metadata, capability descriptions, and routing logic that ASI:One uses to identify appropriate agents for specific tasks. It also supports secure communication and data exchange between agents. The company notes that the directory is platform-agnostic: agents built with any framework can join and interoperate.According to Sheikh, the lack of a discovery layer is one reason most AI agents see little or no usage. “Ninety percent of AI agents never get used because there’s no discovery layer,” he said. He framed the role of Agentverse in more technical terms: “Right now, if you build an agent, there’s no universal way for others to discover it. That’s what AgentVerse solves—it’s like DNS for agents.” He also described the system as an essential component of the emerging agent economy: “Fetch is building the Google of agents. Just like websites needed search, agents need discovery, trust, and interaction—Fetch provides all of that.”The interview further underscored that Agentverse is cloud-agnostic by design. Sheikh contrasted this with competing agent ecosystems tied to specific cloud providers, arguing that a universal registry is only viable if independent of proprietary cloud environments. He said the open architecture enables an LLM to query any agent “within one minute of deployment,” turning agent publication into a near-instantaneous process similar to registering a domain.Agentverse also integrates payment pathways, enabling agents to execute purchases using partners such as Visa, Skyfire, and supported stablecoins. Consumers can configure spending limits or require explicit approval for transactions.<h2>Industry Context and Implications</h2>Fetch’s launch comes at a time when consumer AI platforms are exploring the shift from static chat interfaces toward autonomous agents capable of completing actions. However, most agent systems remain limited by siloed architectures, limited interoperability, and weak verification standards.Fetch positions its infrastructure as a response to these limitations by providing a cross-platform coordination layer, identity system, and directory service. The company argues that an agent ecosystem requires consistent verification mechanisms to ensure that consumers interact with authentic brand representatives rather than imitations. By establishing namespace control and portable trust indicators, Fetch Business aims to fill a gap similar to early web domain verification.At the same time, ASI:One attempts to centralize user preference data in a way that enables more efficient personalization and multi-agent coordination. This approach differs from generalist LLM applications, which often lack persistent preference architectures or direct access to brand-controlled agents.The interview also made clear that micropayments and digital transaction infrastructure are central to Fetch’s long-term vision. Sheikh referenced integrations with protocols such as Coinbase’s 402 and AP2, positioning these capabilities as essential for autonomous agents to complete end-to-end tasks that include financial execution.<h2>Takeaway</h2>Fetch’s combined release of ASI:One, Fetch Business, and Agentverse introduces an interconnected stack designed to support large-scale deployment and usage of AI agents. The company frames the system as foundational infrastructure for an agentic ecosystem, where consumer AIs can coordinate with verified brand agents to complete tasks reliably and securely. The additions to its identity, discovery, and orchestration layers reflect Fetch’s long-standing thesis—rooted partly in lessons from DeepMind’s early development—that intelligence becomes meaningful only when paired with the capacity to act.

أطلقت شركة Fetch AI، وهي شركة ناشئة يقودها هميون شيخ، ثلاثة منتجات مترابطة تهدف إلى تعزيز نظام وكلاء الذكاء الاصطناعي. تشمل العروض الجديدة ASI:One، وهي منصة تنسيق ذكاء اصطناعي شخصي، وFetch Business، وهو بوابة للتحقق والاكتشاف لوكلاء العلامات التجارية، وAgentverse، وهو دليل مفتوح يضم أكثر من مليوني وكيل. تسعى هذه المبادرة إلى إنشاء بنية تحتية قوية لما تصفه Fetch بـ 'الويب الوكالي.'

Fetch AI, una startup dirigida por Humayun Sheikh, ha lanzado tres productos interconectados destinados a mejorar el ecosistema de agentes de IA. Las nuevas ofertas incluyen ASI:One, una plataforma de orquestación de IA personal, Fetch Business, un portal de verificación y descubrimiento para agentes de marca, y Agentverse, un directorio abierto con más de dos millones de agentes. Esta iniciativa busca establecer una infraestructura sólida para lo que Fetch describe como la 'Web Agente.'

Fetch AI, une startup dirigée par Humayun Sheikh, a lancé trois produits interconnectés visant à améliorer l'écosystème des agents IA. Les nouvelles offres comprennent ASI:One, une plateforme d'orchestration d'IA personnelle, Fetch Business, un portail de vérification et de découverte pour les agents de marque, et Agentverse, un annuaire ouvert avec plus de deux millions d'agents. Cette initiative vise à établir une infrastructure robuste pour ce que Fetch décrit comme le 'Web Agentique.'

Fetch AI, a startup led by Humayun Sheikh, has launched three interconnected products aimed at enhancing the ecosystem of AI agents. The new offerings include ASI:One, a personal-AI orchestration platform, Fetch Business, a verification and discovery portal for brand agents, and Agentverse, an open directory with over two million agents. This initiative seeks to establish a robust infrastructure for what Fetch describes as the 'Agentic Web.'

The Google Search of AI agents? Fetch launches ASI:One and Business tier for new era of non-human web

If aesthetics and efficiency top your list of needs, there are several Linux distributions that are right up your alley. Both Ubuntu Budgie and Pop!_OS should top that list.

Ubuntu Budgie vs. Pop!_OS: I've used both Linux distros - here's how to choose

Vous utilisez les Conventional Commits et vous commencez à apprécier la clarté de l’historique Git (si ce n’est pas le cas, <a href="https://dev.to/jpiazzal/conventional-commits-un-premier-pas-vers-lautomatisation-3l5d">voici un article pour le découvrir</a>).

Mais vous continuez à gérer vos versions à la main, écrire le changelog, créer les tags, publier les nouvelles versions…

Et si tout ça se faisait tout seul ? C’est la promesse de <a href="https://github.com/semantic-release/semantic-release" rel="noopener noreferrer">semantic-release</a>.

<blockquote>
Par défaut, semantic-release est étroitement lié à l’écosystème npm, puisqu’il est développé en JavaScript et pensé à l’origine pour les projets Node.js mais certains plugins peuvent exister dans d’autres contextes.
</blockquote>

<h2>
 
 
 Pourquoi semantic-release ?
</h2>

Versionner à la main peut être une source d’erreurs multiple :

<ul>
<li>on oublie d’incrémenter le numéro de version</li>
<li>on modifie le changelog une fois sur deux</li>
<li>on ne sait plus si on doit passer en <code>1.4.2</code> ou <code>1.5.0</code>
</li>
<li>et parfois on publie sans tag</li>
</ul>

semantic-release résout tout ça automatiquement en s’appuyant sur les messages de commit (suivant la norme Conventional Commits).

En clair : vous écrivez votre code, vous faites vos commits correctement, vous mergez et le reste se fait tout seul.

<h2>
 
 
 Comment ça fonctionne ?
</h2>

Tout part de l’analyse des commits depuis la dernière version publiée (ex : <code>1.0.0</code>) :

<ul>
<li>un <code>fix:</code> déclenche une version patch (ex : <code>1.0.1</code>)</li>
<li>un <code>feat:</code> déclenche une version mineure (ex : <code>1.1.0</code>)</li>
<li>un <code>!</code> ou un <code>BREAKING CHANGE</code> déclenche une version majeure (ex : <code>2.0.0</code>)</li>
</ul>

Une fois la version déterminée, semantic-release :

<ol>
<li>met à jour le changelog automatiquement</li>
<li>crée un tag Git</li>
<li>et publie la nouvelle version (sur npm, GitHub, GitLab, etc.)</li>
</ol>

Chaque étapes peut être supprimée ou configurée.

En somme : un cycle de release entièrement piloté par votre historique Git.

<h2>
 
 
 L’écosystème autour de semantic-release
</h2>

semantic-release ne travaille pas seul. Il s’intègre parfaitement avec :

<ul>
<li>
commitlint et Husky, pour vérifier la structure des commits</li>
<li>
GitHub Actions, GitLab CI, ou n’importe quelle pipeline CI/CD</li>
</ul>

Une fois en place, il s’impose comme un maillon essentiel du processus d’intégration continue.

<h2>
 
 
 Mise en place
</h2>

Si vous souhaitez l'intégrer sur votre projet, <a href="https://semantic-release.gitbook.io/semantic-release/usage/getting-started" rel="noopener noreferrer">la documentation officielle</a> est relativement bien faite.

<h2>
 
 
 En résumé
</h2>

Avec semantic-release, vous éliminez toute la partie fastidieuse du versioning et vous rendez votre cycle de release fiable, prévisible et sans effort manuel.

En un mot : publie sans y penser.

يتناول المقال فوائد استخدام semantic-release، وهي أداة مصممة لأتمتة إدارة الإصدارات في تطوير البرمجيات. يبرز التحديات المرتبطة بالنسخ اليدوي، والتي يمكن أن تؤدي إلى أخطاء متعددة، ويؤكد على الوضوح الذي توفره Conventional Commits في تاريخ Git. تم تطوير semantic-release في الأصل لمشاريع Node.js بلغة JavaScript، وتعد بتبسيط العملية من خلال التعامل تلقائيًا مع زيادة الإصدارات، وتوليد سجلات التغييرات، ونشر الإصدارات الجديدة، مما يقلل من احتمال حدوث أخطاء بشرية.

El artículo discute los beneficios de usar semantic-release, una herramienta diseñada para automatizar la gestión de versiones en el desarrollo de software. Destaca los desafíos del versionado manual, que pueden llevar a múltiples errores, y enfatiza la claridad proporcionada por los Conventional Commits en el historial de Git. Semantic-release, desarrollado originalmente para proyectos de Node.js en JavaScript, promete simplificar el proceso al manejar automáticamente los incrementos de versión, la generación de changelogs y la publicación de nuevas versiones, reduciendo así el potencial de error humano.

L'article traite des avantages de l'utilisation de semantic-release, un outil conçu pour automatiser la gestion des versions dans le développement logiciel. Il met en lumière les défis du versionnement manuel, qui peuvent entraîner de multiples erreurs, et souligne la clarté apportée par les Conventional Commits dans l'historique Git. Semantic-release, développé à l'origine pour les projets Node.js en JavaScript, promet de rationaliser le processus en gérant automatiquement les incréments de version, la génération de changelogs et la publication de nouvelles versions, réduisant ainsi le potentiel d'erreur humaine.

The article discusses the benefits of using semantic-release, a tool designed to automate version management in software development. It highlights the challenges of manual versioning, which can lead to multiple errors, and emphasizes the clarity provided by Conventional Commits in Git history. Semantic-release, originally developed for Node.js projects in JavaScript, promises to streamline the process by automatically handling version increments, changelog generation, and publishing new releases, thus reducing the potential for human error.

semantic-release : quand la CI gère nos versions à notre place

arXiv:2209.15409v2 Announce Type: replace 
Abstract: Neural Additive Models (NAMs) have recently demonstrated promising predictive performance while maintaining interpretability. However, their capacity is limited to capturing only first-order feature interactions, which restricts their effectiveness on real-world datasets. To address this limitation, we propose Higher-order Neural Additive Models (HONAMs), an interpretable machine learning model that effectively and efficiently captures feature interactions of arbitrary orders. HONAMs improve predictive accuracy without compromising interpretability, an essential requirement in high-stakes applications. This advantage of HONAM can help analyze and extract high-order interactions present in datasets. The source code for HONAM is publicly available at https://github.com/gim4855744/HONAM/.

تم تقديم نماذج الإضافة العصبية من الدرجة العليا (HONAM) كتحسين على نماذج الإضافة العصبية (NAM) المعروفة بأدائها التنبؤي وقابليتها للتفسير. تتناول HONAM القيود المفروضة على NAM من خلال التقاط تفاعلات الميزات من أوامر عشوائية بشكل فعال، مما يعزز دقة التنبؤ دون المساس بقابلية التفسير، وهو متطلب أساسي في التطبيقات ذات المخاطر العالية. الشيفرة المصدرية لـ HONAM متاحة للجمهور على GitHub.

Los Modelos Aditivos Neurales de Orden Superior (HONAM) se han presentado como un avance sobre los Modelos Aditivos Neurales (NAM), conocidos por su rendimiento predictivo y su interpretabilidad. Los HONAM abordan la limitación de los NAM al capturar de manera efectiva interacciones de características de órdenes arbitrarios, mejorando la precisión predictiva sin comprometer la interpretabilidad, un requisito esencial en aplicaciones de alto riesgo. El código fuente de HONAM está disponible públicamente en GitHub.

Les modèles additifs neuronaux d'ordre supérieur (HONAM) ont été introduits comme une avancée par rapport aux modèles additifs neuronaux (NAM), connus pour leur performance prédictive et leur interprétabilité. Les HONAM surmontent la limitation des NAM en capturant efficacement les interactions entre caractéristiques d'ordres arbitraires, améliorant ainsi la précision prédictive tout en maintenant l'interprétabilité, essentielle pour les applications à enjeux élevés. Le code source des HONAM est disponible publiquement sur GitHub.

Higher-order Neural Additive Models (HONAMs) have been introduced as an advancement over Neural Additive Models (NAMs), which are known for their predictive performance and interpretability. HONAMs address the limitation of NAMs by effectively capturing feature interactions of arbitrary orders, enhancing predictive accuracy while maintaining interpretability, crucial for high-stakes applications. The source code for HONAM is publicly available on GitHub.

Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactions

(My actual stack: simple, powerful, and beginner-friendly)

People overestimate what they need to start an AI-driven business. 
They think they need paid tools, fancy dashboards, or enterprise software.

Truth is, I scaled ReThynk AI, wrote 42+ books, built audiences across platforms, and automated huge parts of my workflow using free tools.

Here are the best ones I relied on every week, with the exact use cases that helped me run multiple brands without chaos. (Note: As I run a research company, I keep switching between tools for research purposes. I use many premium tools as well. )

1. ChatGPT Free Tier: The Core Engine

Yes, the free tier. 
The paid version is amazing, but even the free tier handles:

<ul>
<li>Outlining content</li>
<li>Structuring ideas</li>
<li>Generating variations</li>
<li>Drafting documentation</li>
<li>Writing internal notes</li>
<li>Debugging simple code</li>
<li>Creating mindmaps</li>
</ul>

The trick isn’t the tool. 
The trick is how you think with it.

2. GitHub: My Brain’s Second Hard Drive

I host:

<ul>
<li>Prompt libraries</li>
<li>Documentation</li>
<li>Templates</li>
<li>Frameworks</li>
<li>Experiments</li>
<li>AI workflow scripts</li>
</ul>

GitHub is not a coder’s tool anymore; it’s an intelligence repository. 
Once you start versioning your thinking, you never go back.

3. Notion (Free Plan): My “AI HQ”

I use Notion for:

<ul>
<li>Knowledge base</li>
<li>Content calendar</li>
<li>Prompt archives</li>
<li>Research notes</li>
<li>Project management</li>
</ul>

AI workflows become 10× clearer when you centralise information. 
Notion does that beautifully, even on the free plan.

4. Canva Free: For Fast Brand Assets

I create:

<ul>
<li>Book covers</li>
<li>Thumbnails</li>
<li>Presentation slides</li>
<li>Simple diagrams</li>
<li>Social graphics</li>
</ul>

Not perfect for advanced design, but perfect for speed. 
Speed compounds more than perfection.

5. YouTube Studio: For Running My AI Education Channel

I use it to:

<ul>
<li>Manage lectures</li>
<li>Analyse audience insights</li>
<li>Test titles/thumbnails</li>
<li>Track engagement loops</li>
</ul>

YouTube is one of the best free feedback engines on the planet.

6. Google Drive: Storage + Fast Sharing

Free tools inside Drive = gold:

<ul>
<li>Docs (collaboration)</li>
<li>Sheets (data, logs, planning)</li>
<li>Slides (presentations)</li>
<li>Keep (micro-notes)</li>
</ul>

Most of my ideas start in Google Docs before becoming articles, books, or videos.

7. Readwise (Free Tier): My “Learning Memory”

I use it to collect:

<ul>
<li>Quotes</li>
<li>Research snippets</li>
<li>Highlights</li>
<li>Insights from books</li>
</ul>

Then I reuse these for:

<ul>
<li>Prompt engineering</li>
<li>Books</li>
<li>Dev.to posts</li>
<li>Courses</li>
<li>Workshops</li>
</ul>

Readwise makes your learning compounding instead of disposable.

8. VS Code (Free): For Testing AI-Generated Code

I quickly validate:

<ul>
<li>Scripts</li>
<li>Prototypes</li>
<li>Debug suggestions</li>
<li>Refactored code</li>
<li>Micro-tools</li>
</ul>

AI writes the first version. VS Code helps me check the rest.

Why This Stack Works

Because it’s lightweight, fast, flexible, and zero-friction.

Most people fail because they complicate their stack before they even start.

My philosophy is simple:

<blockquote>
Tools shouldn’t slow you down. 
Tools should disappear into your workflow.
</blockquote>

The best AI operators run lean, not heavy.

My Core Insight

People think “paid tools give leverage.” 
Wrong.

Systems give leverage. 
Thinking gives leverage. 
Your workflow gives leverage.

The tools are just containers. 
What you put inside them, your clarity, reasoning, and consistency, is what creates value.

Final Thought

You don’t need a $500/month tool stack to build an AI-driven career. 
You need:

<ul>
<li>Free tools</li>
<li>Clear thinking</li>
<li>Repeatable workflows</li>
<li>And the courage to publish and ship</li>
</ul>

Everything else is noise.

Start simple. 
Scale intelligently. 
Win consistently.

Next Article

Tomorrow we go deeper:

“Why Prompt Templates Are the New APIs.”

This one will shift how developers think about the next decade of software and AI.

يتناول المقال تجربة الكاتب في إدارة عمل مدفوع بالذكاء الاصطناعي باستخدام أدوات مجانية. ويؤكد أن العديد من رواد الأعمال يبالغون في تقدير الحاجة إلى أدوات مدفوعة وبرامج معقدة لبدء مشاريعهم. يبرز الكاتب فعالية الأدوات المجانية مثل ChatGPT وGitHub وNotion في توسيع أعماله وكتابة أكثر من 42 كتابًا وأتمتة سير العمل. يعمل المقال كدليل لأولئك الذين يسعون للاستفادة من الموارد المتاحة لبناء وإدارة علاماتهم التجارية بكفاءة.

El artículo aborda la experiencia del autor en la gestión de un negocio impulsado por IA utilizando herramientas gratuitas. Se enfatiza que muchos emprendedores sobreestiman la necesidad de herramientas pagadas y software complejo para iniciar sus proyectos. El autor destaca la efectividad de herramientas gratuitas como ChatGPT, GitHub y Notion para escalar su negocio, escribir más de 42 libros y automatizar flujos de trabajo. El artículo sirve como una guía para aquellos que buscan aprovechar recursos accesibles para construir y gestionar sus marcas de manera eficiente.

L'article traite de l'expérience de l'auteur dans la gestion d'une entreprise alimentée par l'IA en utilisant des outils gratuits. Il souligne que de nombreux entrepreneurs surestiment la nécessité d'outils payants et de logiciels complexes pour démarrer leurs projets. L'auteur met en avant l'efficacité d'outils gratuits comme ChatGPT, GitHub et Notion pour développer son entreprise, écrire plus de 42 livres et automatiser les flux de travail. L'article sert de guide pour ceux qui cherchent à tirer parti de ressources accessibles pour construire et gérer leurs marques efficacement.

The article discusses the author's experience in running an AI-driven business using free tools. It emphasizes that many entrepreneurs overestimate the necessity of paid tools and complex software to start their ventures. The author highlights the effectiveness of free tools like ChatGPT, GitHub, and Notion in scaling their business, writing over 42 books, and automating workflows. The article serves as a guide for those looking to leverage accessible resources to build and manage their brands efficiently.

The Best Free Tools I Use to Run an AI-Driven Business

SQL Server 2025 has been <a href="https://techcommunity.microsoft.com/blog/sqlserver/sql-server-2025-is-now-generally-available/4470570" rel="noopener noreferrer">officially announced</a> at Microsoft Ignite 2025 and is now generally available. It had been in public preview since May of 2025 and consumers have been eagerly anticipating the official release of one of Microsoft's most popular software products. I had previous written a fun article where I used AI and historical date like previews, events, and past release dates to try and guess the <a href="https://www.trustedtechteam.com/blogs/sql-server/sql-server-2025-release-date" rel="noopener noreferrer">release date of SQL Server 2025</a>. 

Now it's finally here, and with it comes a whole host of highly anticipated features, most notably AI integration. 

<h2>
 
 
 Major Themes
</h2>

<a href="https://www.trustedtechteam.com/blogs/sql-server/sql-server-2025-new-ai-features" rel="noopener noreferrer">Built-in AI</a> &amp; vector search

<ul>
<li>SQL Server 2025 adds native support for vector-stores/indexing (via DiskANN) enabling semantic search over large datasets. </li>
<li>You can combine traditional keyword SQL queries with vector‐based search in one engine. </li>
<li>Support for retrieval-augmented generation (RAG) patterns, connecting to AI models via REST endpoints, etc. </li>
</ul>

Modern developer productivity enhancements

<ul>
<li>Native JSON support, regular expression support, REST APIs, GraphQL via Data API Builder, etc. </li>
<li>The idea is to let developers build AI-driven/modern applications whether on-premises or cloud with more extensibility. </li>
</ul>

Security, performance &amp; scalability

<ul>
<li>New authentication support via Microsoft Entra ID managed identities and outbound authentication via Azure Arc for hybrid/edge. </li>
<li>Improved query optimization: e.g., persisted statistics on replicas, improved locking mechanisms (TID Locking, LAQ) to reduce contention, improved batch processing and columnstore support for analytics. </li>
</ul>

Hybrid and cloud‐centric analytics &amp; data integration

<ul>
<li>Integration with Microsoft Fabric: near real-time replication of SQL Server data (mirrored database) into OneLake for analytics. </li>
<li>Better support for hybrid cloud, on-premises, and edge scenarios — managing, governing, monitoring across environments with Azure Arc, centralized management etc. </li>
</ul>

<h2>
 
 
 Why this matters
</h2>

<ul>
<li>The database is being positioned as a first‐class AI platform, not just a relational engine.</li>
<li>For companies with large datasets, or those looking to embed AI/semantic search capabilities, this version could significantly change how they build data and app-architectures.</li>
<li>For hybrid/edge scenarios (on-premises + cloud + edge), the enhancements around Azure Arc, Fabric integration, and real-time replication make it easier to maintain consistency, governance, and analytics across environments.</li>
<li>Developers get more flexible tooling (JSON, REST, GraphQL etc) so the barrier to building modern apps on top of the database is lower.</li>
<li>Performance/scalability/security updates mean this is not just “shiny new features” but also foundation</li>
</ul>

تم الإعلان رسميًا عن SQL Server 2025 في مؤتمر Microsoft Ignite 2025 وهو متاح الآن بشكل عام. بعد معاينة عامة منذ مايو 2025، يتضمن الإصدار ميزات متوقعة بشدة، لا سيما دمج الذكاء الاصطناعي، مما يعزز قدراته كواحد من أكثر منتجات البرمجيات شعبية من Microsoft.

SQL Server 2025 ha sido anunciado oficialmente en Microsoft Ignite 2025 y ya está disponible. Después de una vista previa pública desde mayo de 2025, el lanzamiento incluye características muy esperadas, especialmente la integración de IA, mejorando sus capacidades como uno de los productos de software más populares de Microsoft.

SQL Server 2025 a été officiellement annoncé lors de Microsoft Ignite 2025 et est désormais disponible. Après une période de prévisualisation publique depuis mai 2025, cette version comprend des fonctionnalités très attendues, notamment l'intégration de l'IA, renforçant ses capacités en tant que l'un des produits logiciels les plus populaires de Microsoft.

SQL Server 2025 has been officially announced at Microsoft Ignite 2025 and is now generally available. After a public preview since May 2025, the release includes highly anticipated features, particularly AI integration, enhancing its capabilities as one of Microsoft's most popular software products.

SQL Server 2025 is Here!

<h1>
 
 
 AI Amnesia: Erasing Knowledge Without a Trace
</h1>

Imagine your AI model accidentally learned something it shouldn't have – sensitive customer data, for example. Current methods for deleting this information often require retraining the entire model, an expensive and time-consuming process. What if we could surgically remove that knowledge without starting from scratch?

The key lies in a novel approach: creating artificial "forgetting cues." We're teaching the model to unlearn specific data patterns by exposing it to carefully crafted synthetic examples. These examples are designed to strongly contradict the information we want the model to forget, effectively overwriting the problematic associations in its memory. This works even if you don’t have access to the original data you need to erase.

Think of it like this: you're trying to forget a bad song stuck in your head. Instead of trying to actively suppress it (which rarely works), you blast an even more catchy song. The new song overwrites the old one, effectively erasing it from your mental playlist.

Benefits of Selective Forgetting:

<ul>
<li> Enhanced Data Privacy: Remove sensitive data without compromising the overall model's performance.</li>
<li> Reduced Retraining Costs: Avoid full model retraining, saving significant time and resources.</li>
<li> Improved Model Security: Eliminate vulnerabilities introduced by unintentionally learned patterns.</li>
<li> Adaptable Learning: Enables continuous refinement of AI models based on evolving data landscapes.</li>
<li> Compliance Ready: Supports compliance with data privacy regulations like GDPR.</li>
<li> Scalable Solutions: Works efficiently even with limited access to training data.</li>
</ul>

Practical Tip: One challenge is ensuring the synthetic data accurately targets the information you want to remove without negatively impacting the model's ability to generalize. Rigorous testing and validation with holdout datasets are crucial.

The promise of AI that can truly 'forget' opens exciting possibilities for responsible AI development. By enabling precise data deletion, we pave the way for more secure, compliant, and adaptable machine learning systems. Imagine AI models that can adapt to changing ethical guidelines or quickly unlearn incorrect information, all without massive retraining efforts. This is a crucial step towards trustworthy and responsible AI that respects data privacy and aligns with societal values. Future exploration could include extending this to different data modalities and model architectures.

Related Keywords: machine unlearning, data privacy, few-shot learning, zero-shot learning, synthetic data, model editing, catastrophic forgetting, incremental learning, continual learning, deep learning, neural networks, data security, algorithmic fairness, responsible ai, ethical ai, federated unlearning, privacy-preserving ai, model retraining, AI governance, data deletion, GDPR compliance

يتناول المقال نهجًا جديدًا لمعالجة مشكلة نسيان الذكاء الاصطناعي، حيث قد تحتفظ نماذج الذكاء الاصطناعي عن غير قصد بمعلومات حساسة. تتطلب الطرق التقليدية لحذف هذه البيانات غالبًا إعادة تدريب كاملة للنموذج، وهو ما يعد مكلفًا ويستغرق وقتًا. تتضمن التقنية الجديدة إنشاء 'إشارات نسيان' اصطناعية تساعد النموذج على نسيان أنماط بيانات معينة من خلال تعريضه لأمثلة صناعية تتناقض مع المعلومات غير المرغوب فيها، مما يسمح بإزالة المعرفة المستهدفة دون الحاجة للوصول إلى البيانات الأصلية.

El artículo aborda un nuevo enfoque para tratar el problema de la amnesia de la IA, donde los modelos de IA pueden retener inadvertidamente información sensible. Los métodos tradicionales para eliminar estos datos a menudo requieren un reentrenamiento completo del modelo, lo que es costoso y lleva tiempo. La nueva técnica implica crear 'señales de olvido' artificiales que ayudan al modelo a desaprender patrones de datos específicos al exponerlo a ejemplos sintéticos que contradicen la información no deseada, permitiendo así la eliminación selectiva de conocimientos sin necesidad de acceder a l…

L'article traite d'une nouvelle approche pour résoudre le problème de l'amnésie de l'IA, où les modèles d'IA peuvent involontairement conserver des informations sensibles. Les méthodes traditionnelles pour supprimer ces données nécessitent souvent un réentraînement complet du modèle, ce qui est coûteux et long. La nouvelle technique consiste à créer des 'cues d'oubli' artificiels qui aident le modèle à désapprendre des schémas de données spécifiques en lui présentant des exemples synthétiques qui contredisent les informations indésirables, permettant ainsi une suppression ciblée des connaissan…

The article discusses a novel approach to address the issue of AI amnesia, where AI models may inadvertently retain sensitive information. Traditional methods for deleting such data often require complete retraining of the model, which is costly and time-consuming. The new technique involves creating artificial 'forgetting cues' that help the model unlearn specific data patterns by presenting it with synthetic examples that contradict the unwanted information, allowing for targeted knowledge removal without needing access to the original data.

Luminara — A Full Request-Lifecycle HTTP Client Built on Native Fetch

Was this article worth reading? Share it