标签：#an

In November 2025, an engineering team deployed a market research pipeline using four LangChain agents. Due to a logic failure, the "Analyzer" and "Verifier" agents got stuck in a recursive ping-pong loop. Because every individual API call was perfectly valid, the system appeared healthy on their dashboards. 11 days later, they discovered a $47,000 API bill . This is the hidden cost of building autonomous AI: infinite hallucination loops . When an agent encounters an error or fails to reach a termination condition, it will ruthlessly retry, burning through tokens in milliseconds. Why Built-in Controls Fail If you build with LangChain or LangGraph, you are likely relying on two things for cost control: max_iterations : An application-layer limit. LangSmith : An observability dashboard. The problem with max_iterations is that it requires every developer to perfectly hardcode it into every agent. Furthermore, iterations do not equal cost, a single iteration with massive context bloat can still cost a fortune. The problem with LangSmith (and all observability tools) is that they act as a witness, not a circuit breaker. By the time your dashboard alerts you that a spike occurred, the money is already gone. To safely deploy agents to production, you need Agent Runtime Governance , a network-layer firewall that physically drops the HTTP request the exact millisecond a budget hits zero. Enter Loopers . What is Loopers? Loopers is an open-source, baremetal reverse proxy for AI agents. It sits on your critical path between LangChain and your LLM provider (OpenAI, Anthropic, etc.). It uses atomic Redis Lua scripts to reserve budget before the request is sent to the provider. If the agent exceeds its budget, Loopers fails closed and instantly severs the connection, guaranteeing zero budget leakage. Here is how to implement Loopers into your LangChain workflow in less than 5 minutes. Step 1: Spin up the Loopers Firewall Loopers is incredibly lightweight (~40MB RAM) and runs via D

The companies confirmed to TechCrunch that their unusual partnership in Phoenix recently ended after nearly three years..

As Anthropic forges a closer relationship with the state of California, the federal government has made an enemy out of the OpenAI rival.

The Supreme Court's decision to limit geofence warrants is a win for privacy advocates, who called their use unconstitutional but sought an outright ban.

Even if you only use WhatsApp sometimes, you might want to snag your username now to stop giving out your phone number.

Every Sanity marketing site ends up with a page builder. An array of sections, an insert menu, a render loop that maps block._type to a component. You've built it. I've built it. We've all built the same thing. And every one of them ships with the same bug. You add a new section. You wire it into the schema. You add a renderer. You add a component. You add the type. And then — because there are five places to touch and you're a human — you forget one. The section renders blank in production. Or it never shows up in the insert menu. Or it fetches no fields because you missed the GROQ projection, so it renders as nothing at all. No error. No red. Just a hole on the page where a section should be. The annoying part isn't the bug. It's that you'll hit it again on the next project, in exactly the same way, because you rewrote the whole thing from scratch — again. The section tax Here's what "add a section" actually costs in a typical Sanity + Next.js page builder: Schema — a new *Section object type, registered in your schema index. GROQ — a new conditional in the page-builder projection so the block's fields actually come down. Component — the React component that renders it. Renderer map — an entry mapping _type → component. Types — the block variant in whatever union your frontend renders. Miss #2 and the block arrives empty. Miss #4 and it silently skips. Miss #5 and TypeScript shrugs because your union is hand-maintained and now lies. Three different failure modes, all of them quiet, all of them "works on my machine until it doesn't." Now look at those five places and ask: which of them is actually unique to your site? The component is. It's welded to your design system — your spacing, your tokens, your brand. Nobody can reuse it and nobody should. The other four are plumbing . "Look up _type in a map, call the renderer, keep the map in sync with the schema and the query." That code is byte-for-byte the same idea on every project you've ever built. So why is it livi

Director Travis Knight is also the creative mind behind 2016's Oscar-nominated Kubo and the Two Strings .

Where AI incidents in legal actually come from, and what infrastructure (not policy) prevents them. Blake Aber · Predicate Ventures · 2026 The policy layer is table stakes. It isn't enough. When Sullivan & Cromwell apologized to a federal bankruptcy judge in April 2026 for AI hallucinations in a court filing, the firm's apology letter said the firm had policies. Safeguards existed. Those safeguards weren't followed. That framing, "the safeguard existed but wasn't followed," is how a policy failure gets described. But something more specific happened: a hallucination was generated, wasn't caught at generation time, wasn't caught at review time, and made it into a document that got filed. That's not a policy problem. It's an infrastructure problem. The distinction matters because it determines what you build next. What policy can and can't do Policy is a promise made before the event. A well-written AI acceptable-use policy says: don't submit output you haven't reviewed; verify citations before they go into a document; a human must approve anything client-facing. This works when the human executing the task has time, attention, and professional accountability in that moment. It fails when one of those is missing: a deadline, a junior practitioner, a late-night run. Policy can't: Verify a citation at the point of generation Flag output that has drifted below a confidence threshold Stop hallucinated text from appearing in a draft before a human ever sees it Detect when the underlying model is behaving differently than it was in testing Policy can: Set the expectation that review must happen Define who bears accountability when it doesn't Create a paper trail after the fact One of those is prevention. The other is compliance. What infrastructure does instead An AI harness layer operates at the point of generation, not at the point of review. This reflects a broader reality that production AI is mostly harness and very little model . For legal work specifically, three com

Why AI programs at PE portfolio companies stall at the same organizational seam, and what to do about it. Blake Aber · Predicate Ventures · 2026 There's a failure mode I've watched play out at enough portfolio companies that I've given it a name: the ownership dyad. It goes like this. The AI program is running. The product manager owns the roadmap (what the AI should do). Engineering owns the deployment (how it does it). Both parties are competent. Both are aligned on the goal. And the AI initiative quietly stalls anyway, usually somewhere between the promising pilot and the production system that was supposed to follow. The mechanism is diffuse accountability at the decision layer. What the dyad looks like in practice In the average portco planning meeting, the PM and the engineering lead sit across from each other. The PM has a change request: "The model is producing summaries that miss the key clause in contracts above a certain length. We should fix this." Engineering hears this and wants to know: is this a prompt change or a model change? Either requires scoping, and scoping requires the PM's input on acceptable behavior. So engineering asks the PM. The PM says "whatever's best technically." Engineering ships a prompt change. The next month, the same issue appears in a different context. The PM brings it back. Neither person is wrong. Neither person is slacking. The problem is structural: there's no single person who can describe (precisely and completely) what the AI should produce, evaluate whether it's producing it correctly, and approve a change to the system without requiring the other party's sign-off. The dyad looks like shared ownership. It functions as diffuse accountability. No one is in charge of the model's behavior. The failure mode at month nine Most portco AI programs that make it through a successful pilot still die quietly around month nine of production. The most common reason is not that the model got worse. It's that the harness around the m

Xgimi, the Chinese company known for its all-in-one smart projectors, is expanding its portfolio with a new line of screen-equipped smart glasses that first debuted at CES 2026. Unlike AR glasses from companies like Meta and Snap, Xgimi’s new privacy-focused MemoMind One skip cameras for a lighter and more discreet design that helps hide their […]

Target built a generative AI system to improve marketing campaign forecasting by retrieving and ranking similar historical campaigns. Using embeddings, vector search, and LLM ranking, it replaces rule-based workflows. Evaluation shows 75% top-1 and 100% top-3 coverage. The system reduces manual effort, improves consistency, and uses feedback loops to refine retrieval using campaign outcomes. By Leela Kumili

NBCUniversal and Sky will be spun off into separate companies.

Flipper Devices, a company that built a banned hacking device, now wants to hack your attention span.

Erik Steiger discusses the operational pain of legacy PDF generation in regulated banking and manufacturing. He explains how transitioning from resource-heavy engines like Puppeteer and LaTeX to a serverless Rust architecture powered by Typst can drop render latencies below 2ms. He shares how applying Git and Docker concepts to template registries ensures ironclad compliance and rapid debugging. By Erik Steiger

This virtual panel brings together AI security experts to examine the evolution of AI-driven threats, from prompt injection and data poisoning to agent abuse and AI-powered social engineering. The discussion explores emerging attack patterns, incident response challenges, and the changes security teams must make as AI systems become more autonomous and integrated into critical workflows. By Claudio Masolo, Elham Arshad, Sabri Allani, Vijay Dilwale, Igor Maljkovic

Europe’s pro-competition proposals could see Google Search and Android systems opened up. The company claims there are serious privacy flaws.

Nine major suspected cargo thefts happened at Tesla’s Nevada battery factory in January alone, according to sheriff’s records obtained by WIRED.

Anatomy of the Trust Gap Before we can talk about the solution, we need to talk honestly about how...

GitLab's 2026 AI Accountability Report highlights an AI Paradox: although 78% of developers say they code faster, overall software delivery has not accelerated due to downstream testing and review bottlenecks and new challenges for enterprise governance and traceability. By Sergio De Simone

How to Create an AI Agent: A Production Walkthrough The first agent I shipped to production failed at 3am on a Sunday. It looped on a tool call, burned through $40 in tokens before my budget alarm fired, and left a half-written draft in the database with no way to resume. That night taught me more about agent design than any framework tutorial. Since then I have built a pattern I trust enough to leave running unattended for weeks at BizFlowAI, where agents research, write, optimize and publish content without me touching them. This is that pattern, stripped down to what actually matters. Start with the job spec, not the framework Before you pick LangGraph, CrewAI, or roll your own, write the agent's job spec like you would for a junior engineer. One paragraph. What it owns, what it must never do, what "done" looks like, and which signals tell you it failed. Here is the spec for one of my production agents: The Topic Researcher owns generating a ranked list of 20 content topics per site per week. It reads from keyword_pool and search_console_perf , writes to topic_queue . It must never publish, never call paid APIs more than 8 times per run, and must finish in under 6 minutes. Done = 20 topics with score >= 0.6 and zero duplicates against the last 90 days. Failure signal = empty queue after a run, or any topic flagged by the dedupe check. If you cannot write this paragraph, do not build the agent. You will end up with a "do everything" prompt that hallucinates its way through ambiguous tasks. The job spec becomes your evaluation rubric later, so write it carefully. Rule of thumb I use : if the spec needs more than 5 tools or more than 3 decision branches, it is two agents, not one. Design the tools before you write the prompt Most agent failures I have debugged were not prompt failures. They were tool failures. The model called a tool with wrong arguments, the tool returned a 4MB JSON blob, or two tools had overlapping responsibilities and the model picked the wrong