OpenAI's recent restructuring of its for-profit arm to a public benefit corporation is a smart move that will allow the organization to increase its investment opportunities and maintain its nonprofit roots, according to a Northeastern University nonprofit management expert.

أعادت OpenAI هيكلة ذراعها الربحي إلى شركة ذات منفعة عامة، وهي خطوة تُعتبر مفيدة لصناعة الذكاء الاصطناعي. من المتوقع أن يُحسن هذا التغيير فرص الاستثمار مع السماح لـ OpenAI بالحفاظ على جذورها غير الربحية. وصف خبير في إدارة المنظمات غير الربحية من جامعة نورث إيسترن هذه الهيكلة بأنها خطوة ذكية، مشيرًا إلى أنها قد تؤثر بشكل إيجابي على قدرة المنظمة على الابتكار والنمو في المشهد التنافسي للذكاء الاصطناعي. تعكس هذه الخطوة اتجاهًا أوسع نحو تحقيق التوازن بين دوافع الربح والمسؤولية الاجتماعية في التكنولوجيا.

OpenAI ha reestructurado su brazo con fines de lucro en una corporación de beneficio público, un movimiento que se considera beneficioso para la industria de la IA. Se espera que este cambio mejore las oportunidades de inversión mientras permite a OpenAI mantener sus raíces sin fines de lucro. Un experto en gestión de organizaciones sin fines de lucro de la Universidad Northeastern ha descrito esta reestructuración como una decisión inteligente, indicando que podría tener un impacto positivo en la capacidad de la organización para innovar y crecer en el competitivo panorama de la IA. Este cambio refleja una tendencia más amplia a equilibrar los motivos de lucro con la responsabilidad social en la tecnología.

OpenAI a restructuré son bras lucratif en une société à but public, une décision considérée comme bénéfique pour l'industrie de l'IA. Ce changement devrait améliorer les opportunités d'investissement tout en permettant à OpenAI de conserver ses racines à but non lucratif. Un expert en gestion des ONG de l'Université Northeastern a qualifié cette restructuration de décision intelligente, indiquant qu'elle pourrait avoir un impact positif sur la capacité de l'organisation à innover et à se développer dans le paysage concurrentiel de l'IA. Ce changement reflète une tendance plus large à équilibrer les motivations de profit avec la responsabilité sociale dans la technologie.

OpenAI has restructured its for-profit arm into a public benefit corporation, a move that is seen as beneficial for the AI industry. This change is expected to enhance investment opportunities while allowing OpenAI to retain its nonprofit roots. A nonprofit management expert from Northeastern University has described this restructuring as a smart decision, indicating that it could positively impact the organization's ability to innovate and grow within the competitive AI landscape. The shift reflects a broader trend in balancing profit motives with social responsibility in technology.

What does OpenAI's restructuring mean for the future of the AI industry?

<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

Two weeks ago I read a line about tool use with Claude that stuck in my head. Paraphrased:

<blockquote>
Direct tool calls don’t really scale. 
Have the model write code that uses tools, and execute that code instead.
</blockquote>

At the same time, I was knee-deep in wiring a JavaScript execution environment into Contenox, my self-hosted runtime for deterministic, chat-native AI workflows.

So of course the thought was:

<blockquote>
What if I just let the model write the JavaScript and run it inside the runtime? 😅
</blockquote>

This post is about what happened when I tried exactly that.




<h2>
 
 
 What is Contenox?
</h2>

Very short version:

<blockquote>
Contenox is a self-hostable runtime for sovereign GenAI applications. 
It models AI behavior as explicit state machines, not opaque prompt chains.
</blockquote>

Some key properties:

Runtime, not a library, Explicit state machines, Chat-native interface, Vendor-agnostic &amp; self-hosted, written in go with lots of passion and zero tolerance for shortcuts




<h2>
 
 
 The experiment: ask it to fetch and summarize a TODO
</h2>

Once the JS execution hook was in place (a Goja VM with some globals exposed), I wired up a new state machine: 


<div class="highlight js-code-highlight">
<pre class="highlight plaintext"><code>mux_input → moderate → generate_js → run_js → eval_js_result → (repair_js?) → answer
</code></pre>

</div>



Then I opened the Contenox chat UI and typed:

<blockquote>
Me: “Hey Contenox, fetch the TODO item from jsonplaceholder and summarize it.”
</blockquote>

The first attempt didn’t go as planned.

Instead of a neat summary, I got:

<blockquote>
Contenox: 
“I'm sorry, but it seems there was a problem fetching the TODO item from the provided URL due to an Internal Server Error (status code: 500). Unfortunately, I couldn't retrieve any data at this time. My apologies for the inconvenience!”
</blockquote>

I checked manually – Cloudflare was having a moment, JSONPlaceholder was behind it, and the request really was failing. Okay, fair. Long coffee break.

A bit later, I went back to the same chat and typed:

<blockquote>
Me: “okay let's try again now.”
</blockquote>

This time the reply was:

<blockquote>
Contenox: 
<code>Task titled "delectus aut autem" is incomplete. Nothing to summarize here.</code>
</blockquote>

Wait. It worked? Just like that?




<h2>
 
 
 Under the hood: LLM → JavaScript → tools → LLM
</h2>

Looking at the execution trace made it clear what happened.

<h3>
 
 
 1. Input is normalized and moderated
</h3>

The workflow starts with:

<ol>
<li><code>mux_input</code></li>
</ol>

<ul>
<li>
Parses the incoming chat history into a normalized <code>messages</code> array.

<ol>
<li><code>moderate</code></li>
</ol>
</li>
<li>Uses a small model to classify the input as safe/unsafe.</li>
<li>Output: <code>0</code> → safe → continue.</li>
</ul>

So far this is standard workflow stuff.

<h3>
 
 
 2. <code>generate_js</code>: the LLM writes JavaScript
</h3>

Next, the <code>generate_js</code> task runs with a system instruction like:

<ul>
<li>“You are an expert JavaScript agent for the Contenox runtime…”</li>
<li>“You must output JSON: { "code": "" }”</li>
<li>“You can use httpFetch, executeTask, executeTaskChain, …”</li>
<li>“Script must be synchronous, no async/await, and must return a JSON-serializable object.”</li>
</ul>

Given the chat history, the model produced something like this (simplified): 


<div class="highlight js-code-highlight">
<pre class="highlight json"><code>{
 "code": "var result;
var answer;
var meta = { steps: [] };

var todoUrl = \"https://jsonplaceholder.typicode.com/todos/1\";

// Step 1: Fetch the TODO item
meta.steps.push(\"Fetching TODO item from \" + todoUrl);
var fetchResponse = httpFetch(todoUrl);

if (!fetchResponse.ok) {
 answer = \"I couldn't access that item right now because there was some trouble with getting it. Please check the URL or try again later.\";
 meta.error = {
 message: \"HTTP fetch failed\",
 url: todoUrl,
 status: fetchResponse.status,
 statusText: fetchResponse.statusText,
 body: fetchResponse.body,
 error: fetchResponse.error
 };
 result = { answer: answer, meta: meta };
} else {
 var todoItem;
 try {
 todoItem = JSON.parse(fetchResponse.body);
 meta.raw = todoItem;
 } catch (e) {
 answer = \"I fetched the item, but I couldn't understand its format. It doesn't seem to be valid JSON.\";
 meta.error = {
 message: \"JSON parse error\",
 rawBody: fetchResponse.body,
 parseError: e.toString()
 };
 result = { answer: answer, meta: meta };
 }

 if (todoItem) {
 // Step 2: Summarize the TODO item using an LLM
 meta.steps.push(\"Summarizing TODO item with LLM\");
 var prompt = \"Summarize the following TODO item in a concise sentence: \" + JSON.stringify(todoItem);
 var summarizeTask = executeTask(prompt, \"gpt-4o-mini\", \"openai\");

 if (!summarizeTask.success) {
 answer = \"While I managed to fetch your TODO details, the summary tool had a hiccup and couldn't provide me with a concise sentence right now. We seem to be experiencing some temporary issues.\";
 meta.error = {
 message: \"LLM task execution failed\",
 task_id: summarizeTask.task_id,
 error: summarizeTask.error
 };
 result = { answer: answer, meta: meta };
 } else {
 answer = summarizeTask.response;
 meta.llmResponse = summarizeTask.response;
 result = { answer: answer, meta: meta };
 }
 }
}

result;"
}
</code></pre>

</div>



A few important details here:

<ul>
<li>
It encodes error handling:

<ul>
<li>If HTTP fails → user-friendly <code>answer</code>, raw error in <code>meta.error</code>.</li>
<li>If JSON parse fails → similar pattern.</li>
<li>If the inner LLM call fails → fallback message.</li>
</ul>


</li>

<li>It delegates the actual summarization to another model via <code>executeTask</code>.</li>

<li>It returns a structured <code>result</code> with both <code>answer</code> and <code>meta</code>.</li>

</ul>

This is not the model “calling tools” directly. It’s the model writing a program that calls tools.

<h3>
 
 
 3. <code>run_js</code>: execute the code in a sandbox
</h3>

The next task is <code>run_js</code>, which is just a Contenox <code>hook</code> that calls the JS sandbox: 


<div class="highlight js-code-highlight">
<pre class="highlight json"><code>{
 "name": "js_sandbox",
 "tool_name": "execute_js",
 "args": {
 "code": "{{.generate_js.code}}"
 }
}
</code></pre>

</div>



Inside the trace you can see:

<ul>
<li>An <code>httpFetch</code> log for the JSONPlaceholder URL.</li>
<li>A response with <code>status: 200 OK</code> when things finally worked.</li>
<li>
An <code>executeTask</code> log with the summarization prompt:

<ul>
<li><code>Summarize the following TODO item in a concise sentence: {"userId":1,"id":1,"title":"delectus aut autem","completed":false}</code></li>
</ul>


</li>

</ul>

The sandbox result looked roughly like: 


<div class="highlight js-code-highlight">
<pre class="highlight json"><code>{
 "ok": true,
 "result": {
 "answer": "Task titled \"delectus aut autem\" is incomplete.",
 "meta": {
 "llmResponse": "Task titled \"delectus aut autem\" is incomplete.",
 "raw": {
 "userId": 1,
 "id": 1,
 "title": "delectus aut autem",
 "completed": false
 },
 "steps": [
 "Fetching TODO item from https://jsonplaceholder.typicode.com/todos/1",
 "Summarizing TODO item with LLM"
 ]
 }
 },
 "logs": [ ... ],
 "code": "var result; ..."
}
</code></pre>

</div>



<h3>
 
 
 4. <code>eval_js_result</code>: success or retry?
</h3>

Now comes the evaluator:

<ul>
<li>It receives a description of the JS sandbox output.</li>
<li>
The system prompt is very strict:

<ul>
<li>If <code>ok</code> is true and there is a non-empty <code>result.answer</code> → respond with <code>success</code>.</li>
<li>Otherwise → respond with <code>retry</code>.</li>
</ul>


</li>

</ul>

On the successful run, it answered: 


<div class="highlight js-code-highlight">
<pre class="highlight plaintext"><code>success
</code></pre>

</div>



So the workflow does not go into <code>repair_js</code> or <code>run_js_retry</code>. Happy path.

<h3>
 
 
 5. <code>answer</code>: extract the final user message
</h3>

The final task, <code>answer</code>, is intentionally boring:

<ul>
<li>System prompt: “You are a purely extractive post-processor. Do NOT invent content. Just surface the best existing <code>answer</code> field.”
</li>
<li>
It gets:

<ul>
<li>First run (<code>run_js</code> result).</li>
<li>Second run (<code>run_js_retry</code>), if any.</li>
</ul>


</li>

<li>

Selection rule:

<ul>
<li>Take the last non-empty <code>answer</code> you see.</li>
<li>Output it verbatim.</li>
</ul>


</li>

</ul>

In our case it found: 


<div class="highlight js-code-highlight">
<pre class="highlight plaintext"><code>Task titled "delectus aut autem" is incomplete.
</code></pre>

</div>



And that’s exactly what Contenox replied in chat.




<h2>
 
 
 Why this is interesting (to me, at least)
</h2>

What I originally set out to build:

<blockquote>
A runtime for deterministic, observable GenAI workflows. 
Tasks, transitions, hooks – all explicit and replayable.
</blockquote>

What I accidentally stumbled into:

<blockquote>
A multi-model, self-orchestrating agent pattern, 
where LLMs write code that uses tools, and the runtime executes and evaluates that code.
</blockquote>

The pattern looks like this:

<ol>
<li>
Planner LLM (<code>generate_js</code>)</li>
</ol>

<ul>
<li>Reads user intent + history.</li>
<li>Emits JavaScript that calls <code>httpFetch</code>, <code>executeTask</code>, <code>executeTaskChain</code>, hooks, etc.</li>
</ul>

<ol>
<li>
Execution environment (<code>run_js</code> in Goja)</li>
</ol>

<ul>
<li>Deterministic execution of that JS.</li>
<li>Full logs of every HTTP call, every inner LLM call, every step.</li>
</ul>

<ol>
<li>
Controller LLM (<code>eval_js_result</code>)</li>
</ol>

<ul>
<li>Looks at the sandbox result.</li>
<li>Decides: is this good enough? Retry? Repair?</li>
</ul>

<ol>
<li>
Repair LLM (<code>repair_js</code>, if needed)</li>
</ol>

<ul>
<li>Gets the previous code + error output.</li>
<li>Writes a fixed version of the JS.</li>
</ul>

<ol>
<li>
Answer LLM (<code>answer</code>)</li>
</ol>

<ul>
<li>Doesn’t “reason” at all.</li>
<li>Just extracts the final <code>answer</code> text safely.</li>
</ul>

All of that is expressed as an explicit state machine in Contenox.

No hidden loops, no undocumented retries, no magic glue code inside some SDK. It’s all visible in the workflow graph and trace.




To me, that’s the exciting part:

<blockquote>
You don’t have to choose between “boring deterministic workflows” and “fancy agents”. 
You can build the agent on top of deterministic workflows. 
And everything stays **self-hosted, inspectable, and auditable if you want.
</blockquote>

يتناول المقال تجربة تم فيها السماح لنموذج ذكاء اصطناعي بكتابة كود جافا سكريبت داخل بيئة مستقلة تُدعى كونتينوكس. يتأمل الكاتب في مفهوم يتعلق باستخدام الأدوات في الذكاء الاصطناعي، مقترحًا أن النماذج يجب أن تولد كودًا لاستخدام الأدوات بدلاً من إجراء مكالمات مباشرة. تم اختبار هذا النهج من خلال تنفيذ كود جافا سكريبت الذي تم إنشاؤه داخل بيئة كونتينوكس، بهدف تحسين كفاءة سير العمل في الذكاء الاصطناعي.

El artículo discute un experimento en el que se permitió a un modelo de IA escribir código JavaScript dentro de un entorno autónomo llamado Contenox. El autor reflexiona sobre un concepto relacionado con el uso de herramientas en IA, sugiriendo que los modelos deberían generar código para utilizar herramientas en lugar de realizar llamadas directas. Este enfoque se probó ejecutando el JavaScript generado dentro del entorno Contenox, con el objetivo de mejorar la eficiencia de los flujos de trabajo de IA.

L'article traite d'une expérience où un modèle d'IA a été autorisé à écrire du code JavaScript au sein d'un environnement autonome appelé Contenox. L'auteur réfléchit à un concept concernant l'utilisation des outils en IA, suggérant que les modèles devraient générer du code pour utiliser des outils plutôt que d'effectuer des appels directs. Cette approche a été testée en exécutant le JavaScript généré dans l'environnement Contenox, visant à améliorer l'efficacité des flux de travail en IA.

The article discusses an experiment where an AI model was allowed to write JavaScript code within a self-hosted runtime called Contenox. The author reflects on a concept regarding tool usage in AI, suggesting that models should generate code to utilize tools instead of direct calls. This approach was tested by executing the generated JavaScript within the Contenox environment, aiming to enhance the efficiency of AI workflows.

I Let an LLM Write JavaScript Inside My AI Runtime. Here’s What Happened

<h1>
 
 
 Sector HQ Weekly Digest - November 17, 2025
</h1>

Who's shipping vs who's just talking? Here's this week's AI industry intelligence.

<h2>
 
 
 🏆 Top 10 Companies
</h2>

<ol>
<li>
OpenAI - Score: 442385.7 | 343 events this week</li>
<li>
Anthropic - Score: 266113.1 | 51 events this week</li>
<li>
Amazon - Score: 135242.8 | 22 events this week</li>
<li>
Nvidia - Score: 128360.7 | 161 events this week</li>
<li>
Google - Score: 111135.8 | 125 events this week</li>
<li>
Microsoft - Score: 95559.7 | 99 events this week</li>
<li>
Meta - Score: 78015.6 | 61 events this week</li>
<li>
Apple - Score: 64936.3 | 94 events this week</li>
<li>
Tesla - Score: 41242.1 | 12 events this week</li>
<li>
AMD - Score: 40235.9 | 43 events this week</li>
</ol>

<h2>
 
 
 📈 Biggest Movers
</h2>

<ul>
<li>↑ Sony jumped 277 positions to #58</li>
<li>↑ Stability AI jumped 183 positions to #78</li>
<li>↑ Bytedance jumped 143 positions to #68</li>
<li>↑ Scale AI jumped 122 positions to #66</li>
<li>↑ Palantir jumped 107 positions to #17</li>
</ul>

<h2>
 
 
 🚨 Hype Gap Alerts
</h2>

No high hype alerts this week

<h2>
 
 
 📊 Key Insights
</h2>

<ul>
<li>Total companies tracked: 100</li>
<li>Total events this week: 1317</li>
<li>Average activity per company: 13.2 events</li>
</ul>

<h2>
 
 
 💡 What This Means
</h2>

The AI industry continues to evolve rapidly. Companies that ship consistently rise in our rankings, while those focused on hype alone get flagged by our Hype Gap detector.

Methodology: Our leaderboard tracks real product releases, funding events, partnerships, and market traction - not just PR and social media buzz.




Want real-time updates? Check out the live leaderboard at <a href="https://sectorhq.co" rel="noopener noreferrer">sectorhq.co</a>

Track specific companies and get instant alerts when they move in the rankings.

<h2>
 
 
 Tags
</h2>

<h1>
 
 
 AI #ArtificialIntelligence #MachineLearning #TechIndustry #Startups #AILeaderboard
</h1>

تسليط الضوء على أحدث التطورات في صناعة الذكاء الاصطناعي في نشرة قطاع HQ الأسبوعية بتاريخ 17 نوفمبر 2025، مع التركيز على أداء الشركات الرائدة. تتصدر OpenAI القائمة برصيد 442385.7 و343 حدثًا، تليها Anthropic وAmazon. كما يشير التقرير إلى تحركات كبيرة، حيث قفزت Sony 277 مركزًا في الترتيب، مما يعكس الطبيعة الديناميكية للقطاع.

El Digest semanal de Sector HQ del 17 de noviembre de 2025 destaca los últimos desarrollos en la industria de la IA, centrándose en el rendimiento de las principales empresas. OpenAI lidera con una puntuación de 442385.7 y 343 eventos, seguido de Anthropic y Amazon. El informe también señala movimientos significativos, con Sony saltando 277 posiciones en el ranking, reflejando la naturaleza dinámica del sector de la IA.

Le Digest hebdomadaire du Secteur HQ du 17 novembre 2025 met en lumière les derniers développements de l'industrie de l'IA, en se concentrant sur la performance des principales entreprises. OpenAI est en tête avec un score de 442385,7 et 343 événements, suivi d'Anthropic et d'Amazon. Le rapport note également des mouvements significatifs, Sony ayant grimpé de 277 positions dans le classement, reflétant la nature dynamique du secteur de l'IA.

The Sector HQ Weekly Digest for November 17, 2025, highlights the latest developments in the AI industry, focusing on the performance of top companies. OpenAI leads with a score of 442385.7 and 343 events, followed by Anthropic and Amazon. The report also notes significant movements, with Sony jumping 277 positions in the rankings, reflecting the dynamic nature of the AI sector.

Sector HQ Weekly Digest - November 17, 2025

arXiv:2511.10693v1 Announce Type: new 
Abstract: Voice-based artificial intelligence is increasingly expected to adhere to human social conventions, but can it learn implicit cues that are not explicitly programmed? This study investigates whether state-of-the-art text-to-speech systems have internalized the human tendency to reduce speech rate to convey politeness - a non-obvious prosodic marker. We prompted 22 synthetic voices from two leading AI platforms (AI Studio and OpenAI) to read a fixed script under both "polite and formal" and "casual and informal" conditions and measured the resulting speech duration. Across both AI platforms, the polite prompt produced slower speech than the casual prompt with very large effect sizes, an effect that was statistically significant for all of AI Studio's voices and for a large majority of OpenAI's voices. These results demonstrate that AI can implicitly learn and replicate psychological nuances of human communication, highlighting its emerging role as a social actor capable of reinforcing human social norms.

تدرس دراسة حديثة نُشرت على arXiv ما إذا كانت أنظمة تحويل النص إلى كلام المتقدمة يمكن أن تتعلم الفروق الاجتماعية، وخاصة الميل البشري لتقليل سرعة الكلام للتعبير عن الأدب. اختبر الباحثون 22 صوتًا صناعيًا من AI Studio وOpenAI في ظروف رسمية وغير رسمية، ووجدوا أن العبارات المهذبة أدت إلى كلام أبطأ بشكل كبير عبر كلا النظامين. يشير هذا إلى أن الذكاء الاصطناعي يمكن أن يستوعب ويعيد إنتاج الإشارات النفسية الدقيقة في التواصل البشري.

Un estudio reciente publicado en arXiv investiga si los sistemas avanzados de texto a voz pueden aprender matices sociales, específicamente la tendencia humana a reducir la velocidad del habla para transmitir cortesía. Los investigadores probaron 22 voces sintéticas de AI Studio y OpenAI en condiciones de cortesía y casualidad, encontrando que los mensajes corteses resultaron en un habla significativamente más lenta en ambas plataformas. Esto sugiere que la IA puede internalizar y replicar sutiles señales psicológicas en la comunicación humana.

Une étude récente publiée sur arXiv examine si les systèmes avancés de synthèse vocale peuvent apprendre des nuances sociales, en particulier la tendance humaine à ralentir la parole pour exprimer la politesse. Les chercheurs ont testé 22 voix synthétiques d'AI Studio et d'OpenAI dans des conditions polies et décontractées, constatant que les prompts polis entraînaient un discours significativement plus lent sur les deux plateformes. Cela suggère que l'IA peut intérioriser et reproduire des indices psychologiques subtils dans la communication humaine.

A recent study published on arXiv investigates whether advanced text-to-speech systems can learn social nuances, specifically the human tendency to slow speech for politeness. Researchers tested 22 synthetic voices from AI Studio and OpenAI under polite and casual conditions, finding that the polite prompts resulted in significantly slower speech across both platforms. This suggests that AI can internalize and replicate subtle psychological cues in human communication.

Do AI Voices Learn Social Nuances? A Case of Politeness and Speech Rate

Building RSSRenaissance: AI-Powered Summaries for Smarter Reading

When I set out to build RSSRenaissance, my goal was simple: create a tool that helps users stay informed without drowning in endless articles. With the sheer volume of tech, news, and educational content available online, I wanted a solution that could fetch feeds, summarize content, and deliver actionable insights instantly.

Inspiration

I was inspired by the challenge of managing information efficiently. As a developer and someone who constantly explores new tech trends, I realized that even curated feeds can be overwhelming. I wanted a platform that doesn’t just deliver content but distills it intelligently.

What RSSRenaissance Does

Fetches RSS feeds from multiple sources like TechCrunch, The Verge, and Ars Technica.

Processes and stores feed items in a PostgreSQL database with caching via Redis.

Uses AI to generate instant summaries of articles, helping users quickly grasp key points.

Offers a modern Next.js interface for smooth reading and interaction.

How I Built It

I leveraged Next.js API routes as the backend, integrated with PostgreSQL and Redis for persistence and caching. AI-generated summaries were powered by OpenAI models. Throughout development, I used Kiro for:

Generating boilerplate code

Building reusable components

Writing TypeScript types and validation schemas

Streamlining backend feed ingestion workflows

The development workflow was a combination of spec-driven prompts and iterative “vibe coding” with Kiro, which significantly accelerated the process.

Challenges I Faced

Parsing feeds reliably across different formats (RSS, Atom, XML).

Handling API rate limits and network failures gracefully.

Ensuring that AI-generated summaries were accurate, concise, and user-friendly.

Kiro helped overcome many of these challenges by generating precise TypeScript definitions, building robust error handling, and suggesting scalable architecture patterns.

Accomplishments I’m Proud Of

A fully functional AI-assisted RSS feed reader with summarization.

Deployment-ready Docker setup with worker queues and health checks.

Clean, modular codebase that separates frontend, backend, and worker logic.

Integration of real-time caching with Redis for fast feed updates.

What I Learned

How to architect Next.js projects for both frontend and backend APIs.

Efficiently integrating AI summarization into production workflows.

How to leverage Kiro’s prompts to speed up development without sacrificing quality.

What’s Next for RSSRenaissance

Adding user personalization for preferred feeds and topics.

Expanding AI summarization to include actionable recommendations.

Improving frontend UX with dashboards, search, and feed management.

RSSRenaissance demonstrates how AI can transform information consumption—making knowledge accessible, digestible, and actionable.

يهدف مشروع RSSRenaissance إلى إنشاء أداة تساعد المستخدمين على البقاء على اطلاع دون أن يشعروا بالارتباك بسبب كثرة المقالات. تقوم المنصة بجلب خلاصة RSS من مصادر متعددة مثل TechCrunch وThe Verge، وتعالجها باستخدام قاعدة بيانات PostgreSQL، وتستخدم الذكاء الاصطناعي لإنشاء ملخصات فورية. وهذا يمكّن المستخدمين من فهم النقاط الرئيسية بسرعة.

RSSRenaissance tiene como objetivo crear una herramienta que ayude a los usuarios a mantenerse informados sin sentirse abrumados por un exceso de artículos. La plataforma obtiene feeds RSS de diversas fuentes como TechCrunch y The Verge, los procesa utilizando una base de datos PostgreSQL y emplea IA para generar resúmenes instantáneos. Esto permite a los usuarios captar rápidamente los puntos clave del contenido.

RSSRenaissance vise à créer un outil qui aide les utilisateurs à rester informés sans être submergés par un trop grand nombre d'articles. La plateforme récupère des flux RSS de diverses sources comme TechCrunch et The Verge, les traite à l'aide d'une base de données PostgreSQL et utilise l'IA pour générer des résumés instantanés. Cela permet aux utilisateurs de saisir rapidement les points clés du contenu.

Building RSSRenaissance aims to create a tool that helps users stay informed without being overwhelmed by excessive articles. The platform fetches RSS feeds from various sources like TechCrunch and The Verge, processes them using a PostgreSQL database, and employs AI to generate instant summaries. This allows users to quickly grasp key points from the content.

Building RSSRenaissance: AI-Powered Summaries for Smarter Reading

Computer-aided design (CAD) is the go-to method for designing most of today's physical products. Engineers use CAD to turn 2D sketches into 3D models that they can then test and refine before sending a final version to a production line. But the software is notoriously complicated to learn, with thousands of commands to choose from. To be truly proficient in the software takes a huge amount of time and practice.

تم تطوير وكيل ذكاء اصطناعي جديد يمكنه إنشاء كائنات ثلاثية الأبعاد من رسومات ثنائية الأبعاد باستخدام برنامج التصميم بمساعدة الكمبيوتر (CAD). يعد CAD أساسيًا للمهندسين في تصميم المنتجات المادية، ولكنه غالبًا ما يكون معقدًا ويتطلب وقتًا طويلاً لإتقانه. قد تبسط هذه التطورات عملية التصميم وتحسن الإنتاجية في مجالات الهندسة المختلفة.

Se ha desarrollado un nuevo agente de IA que puede crear objetos 3D a partir de bocetos 2D utilizando software de diseño asistido por computadora (CAD). El CAD es esencial para que los ingenieros diseñen productos físicos, pero a menudo es complejo y requiere mucho tiempo para dominarlo. Este avance podría simplificar el proceso de diseño y mejorar la productividad en varios campos de la ingeniería.

Un nouvel agent d'IA a été développé pour créer des objets 3D à partir de croquis 2D en utilisant un logiciel de conception assistée par ordinateur (CAO). La CAO est essentielle pour les ingénieurs dans la conception de produits physiques, mais elle est souvent complexe et nécessite beaucoup de temps pour être maîtrisée. Cette avancée pourrait simplifier le processus de conception et améliorer la productivité dans divers domaines de l'ingénierie.

A new AI agent has been developed that can create 3D objects from 2D sketches using computer-aided design (CAD) software. CAD is essential for engineers to design physical products, but it is often complex and time-consuming to master. This advancement could simplify the design process and enhance productivity in various engineering fields.

AI agent learns to create 3D objects from sketches using CAD software

The global investment frenzy around AI has seen companies valued at trillions of dollars and eye-watering projections of how it will boost economic productivity.

لقد أدت جنون الاستثمار العالمي حول الذكاء الاصطناعي (AI) إلى تقييم الشركات بمليارات الدولارات، مع توقعات متفائلة حول إمكانيته في تعزيز الإنتاجية الاقتصادية. ومع ذلك، تزداد المخاوف بشأن استدامة هذا الازدهار مع ارتفاع تقلبات السوق التي تثير تساؤلات حول مستقبل الاستثمارات في الذكاء الاصطناعي.

La locura de inversión global en inteligencia artificial (IA) ha llevado a que las empresas sean valoradas en billones de dólares, con proyecciones optimistas sobre su potencial para aumentar la productividad económica. Sin embargo, hay crecientes preocupaciones sobre la sostenibilidad de este auge, ya que las fluctuaciones del mercado plantean preguntas sobre el futuro de las inversiones en IA.

La frénésie d'investissement mondial autour de l'intelligence artificielle (IA) a conduit à des valorisations d'entreprises atteignant des milliers de milliards de dollars, avec des projections optimistes sur son potentiel à améliorer la productivité économique. Cependant, des inquiétudes croissantes se font sentir quant à la durabilité de cet essor alors que les fluctuations du marché soulèvent des questions sur l'avenir des investissements dans l'IA.

The global investment frenzy surrounding artificial intelligence (AI) has led to companies being valued at trillions of dollars, with optimistic projections about its potential to enhance economic productivity. However, there are growing concerns about the sustainability of this boom as market fluctuations raise questions about the future of AI investments.

Is the AI bubble about to burst? What to watch for as the markets wobble

Imagine a world in which a humanoid robot cares for you when you need help and support with daily activities.

يتناول المقال مفهوم 'روبوتات الرعاية'، وهي روبوتات شبيهة بالبشر مصممة لمساعدة الأفراد في الأنشطة اليومية. يثير المقال تساؤلات حول الآثار المترتبة على دمج هذه التكنولوجيا في الرعاية الشخصية والمخاوف المحتملة المتعلقة باستخدامها.

El artículo discute el concepto de 'carebots', robots humanoides diseñados para ayudar a las personas con actividades diarias. Plantea preguntas sobre las implicaciones de integrar esta tecnología en el cuidado personal y las preocupaciones potenciales en torno a su uso.

L'article aborde le concept des 'carebots', des robots humanoïdes conçus pour aider les individus dans leurs activités quotidiennes. Il soulève des questions sur les implications de l'intégration de cette technologie dans les soins personnels et les préoccupations potentielles liées à leur utilisation.

The article discusses the concept of 'carebots,' humanoid robots designed to assist individuals with daily activities. It raises questions about the implications of integrating such technology into personal care and the potential concerns surrounding their use.

What does OpenAI's restructuring mean for the future of the AI industry?

Was this article worth reading? Share it