All news

Building the Claude API for the Frontier: Inside Claude Platform's Release and Safety Decisions

Claude Platform engineers Jake Dejno and Lucca Siaudzionis explain how the Claude API evolves alongside each model launch, covering feature release decisions, model versioning and migrations, and cost management. They detail best practices for changing effort mid-conversation without breaking prompt caching, and how Claude Mythos and Fable share the same model weights with different safeguards. Claude Managed Agents and mid-conversation effort changes are in beta, and Mythos access runs through the Cyber Verification Program.

How H6.ai builds AI-powered financial automation with Lakebase Postgres

H6.ai automates accounts payable on top of customers' existing ERPs, using a dedicated Lakebase Postgres database per customer as its system of record. Because invoice data keeps changing, the team uses Lakebase copy-on-write branches to freeze snapshots of customer databases and run each regression test on its own short-lived branch, so the live database is never written to. Each run is judged by deterministic assertions plus a panel of AI judges from different model providers.

Databricks launches Lakehouse//RT to serve real-time analytics without proportional cost growth

Databricks introduced Lakehouse//RT, a real-time analytics engine that runs high-concurrency workloads directly on lakehouse data and is now available in beta. The company says it delivers sub-100 millisecond latency at 12,000 queries per second, adds capacity one node at a time, and avoids a separate serving layer; customers Aurasell, VisionHeight and nOps report 6x to 10x lower infrastructure costs after migrating from multi-cluster setups, Apache Pinot and Apache Druid.

Five ways Jensen Huang's ouster from Nvidia could damage the AI industry

TechCrunch's Julie Bort argues that Jensen Huang's removal as Nvidia CEO over admitted affairs, including one with an executive at a Singapore-based neocloud suspected of smuggling Nvidia chips to China, costs the AI industry its most prominent advocate. She lists five areas left without their biggest champion: open-weight models, industry self-regulation of AI agent security, the argument that AI is an engineered tool rather than a life form, the new Nvidia-powered AI PC line due this holiday season, and the circular deals and financing arrangements backing data center build-outs. Bort notes Nvidia had agreed to acquire Hugging Face for $12.9 billion and had committed to $750 billion in such deals as of July, per Bloomberg.

Jensen Huang agrees to testify before Congress by Thanksgiving

Former Nvidia CEO Jensen Huang has agreed to testify before Congress by Thanksgiving, House Foreign Affairs Committee Chairman Brian Mast said Thursday, after senior lawmakers threatened to subpoena him. The closed-door testimony follows a November 4 letter from Mast, John Moolenaar and Rick Crawford requesting his appearance before their committees, and Mast said he expects the briefing to be recorded on video and transcribed. Huang stepped down as CEO following reports of an alleged affair with a woman suspected of spying for China.

Jensen Huang resigns from Nvidia as China spy scandal unfolds

Jensen Huang has resigned as Nvidia CEO after reports of his affairs, including one with an alleged Chinese spy, threatened to engulf the company, The Verge's Decoder reports. In an interview recorded two days before the resignation, Brookings fellow Kyle Chan said Beijing's likely aim was visibility into US policymaking and influence over export controls rather than chip designs, since Nvidia was already selling to intermediary Megaspeed. Chan said the controversy could weaken the camp arguing for looser chip export controls and strengthen calls in Congress for a full investigation.

Same event; the pick carries“NVIDIA Announces CEO Transition as Jensen Huang Resigns, Colette Kress Named Interim CEO”

Amazon Bedrock AgentCore Evaluations: Built-in, DeepEval and AutoEval evaluators

Amazon Bedrock AgentCore Evaluations now lets teams run AWS built-in evaluators alongside managed DeepEval and AutoEval metrics, plus custom evaluators derived from either. The built-in catalog spans 15 evaluators across response quality, goal completion, tool use, skills and safety, with three trajectory checks for expected tool paths. DeepEval adds multi-turn metrics such as ConversationCompleteness and KnowledgeRetention, while AutoEval contributes specialized signals including security.

Building a Daily Dependency Watcher with LangGraph and Amazon Bedrock AgentCore Web Search

The Web Search API in Amazon Bedrock AgentCore is now available, giving agents current web results through a single SigV4-signed API call served from a web index Amazon operates. A walkthrough builds a daily dependency watch as a LangGraph graph that researches npm, PyPI, and container base images in parallel, with date windows, blocklists, and search budgets enforced in code. In testing, the three branches finished in 36 seconds versus 99 seconds run sequentially.

Moonshot AI's Kimi K3.1 Pro Highspeed launches on Amazon Bedrock

Moonshot AI's Kimi K3.1 Pro Highspeed is now available on Amazon Bedrock, a post-trained version of Kimi K3 with the same 3T-class open-weight architecture and 1-million-token context window, trained with more post-training compute for long-horizon agentic work and fewer factual errors. Moonshot AI reports 2–3 times the output speed of Kimi K3.1 Pro, and existing Kimi K3 users can switch by changing the model ID. The post shows Chat Completions, Responses and Converse API calls, the Flex tier at half the Standard price, explicit prompt caching with prompt_cache_breakpoint, and connecting the model to the OpenCode coding agent.

Amazon SageMaker AI bidirectional streaming gains usage-based pricing, Deepgram as launch partner

Amazon SageMaker AI bidirectional streaming now supports usage-based metering, letting model providers report actual consumption to AWS Marketplace software charges while endpoint infrastructure fees still apply. Deepgram is the launch partner, bringing usage-based Speech-to-Text and Text-to-Speech billing to AWS Marketplace. The design adds a companion WebSocket metadata stream, capped at one message per second and 512 bytes, so providers can send incremental metering records during live sessions.

AWS open-sources UAEF, a framework-agnostic evaluation system for AI agents

AWS has open-sourced UAEF (Universal Agent Evaluation Framework), a framework-agnostic system that uses adapters to normalize agent traces from LangGraph, LangChain, Strands Agents, Amazon Bedrock AgentCore and Langfuse into one canonical AgentTrace, then scores them with 36 built-in metrics across 7 dimensions. Results are stored per experiment in Amazon DynamoDB and Amazon S3, so teams can compare agent versions against a baseline, flag regressions with a default 5 percent threshold, and generate statistical reports plus LLM-written insights. The post says customers across 12 organizations in telecom, healthcare and financial services used UAEF before release, and the Apache 2.0 code, Python library, CDK deployment and per-framework notebooks are in the awslabs/uaef GitHub repository.

AWS Quick AI-PDLC: Six Agents for AI-Driven Product Development

AWS Quick introduces AI-PDLC, a framework of six specialized agents—led by an Orchestrator covering Discovery, Prioritize, Working Backwards, Spec Generator, and Designer—that turns scattered enterprise signals from Slack, Jira, Salesforce and SharePoint into a traceable prototype_spec.md. Every phase requires human approval, and the spec can be handed to coding agents like Kiro or Claude Code via the open Agent Client Protocol (ACP).

AWS opens catalog of 23 reusable generative AI assets from its Innovation Center

AWS has published a catalog of 23 production-ready, open source generative AI assets from its Generative AI Innovation Center, now part of AWS Frontier AI Engineering & Services. The building blocks cover RAG pipelines, document processors, agent scaffolding and evaluation frameworks, and AWS says they can cut development from months to weeks. DoorDash reported a 50x increase in testing capacity and Ricoh a 7-fold throughput increase after building on the assets.

How DXC Technology built a multi-model AI substrate on Amazon Bedrock

DXC Technology built the model substrate for its DXC OASIS IT-operations harness on Amazon Bedrock, reaching Anthropic Claude, Amazon Nova, Meta Llama and open-weight models through one managed interface. Amazon Bedrock Guardrails apply content filtering, PII redaction and denied-topic policies uniformly across every model, while AWS PrivateLink keeps inference traffic inside the customer VPC. DXC OASIS has been generally available since March 2026 and cut resolution time by 95% on average across 56 measured use cases.

Agent DLC: Engineering AI Agents from Prototype to Production

AWS introduces the Agent Development Lifecycle (Agent DLC), a framework with one lifecycle, two loops, and a single explicit standard for judging every agent change. It addresses three agent properties that break conventional CI/CD: non-determinism, prompts as source code, and independently moving dependencies. A reference HR policy assistant shows chunk-level retrieval precision of 1.00 across all three test questions while fact-level precision fell to 0.09 and retrieval coverage hit 0.00 on one question.

Fine-grained access control for Amazon Bedrock Managed Knowledge Base tools

AWS shows how to give a shared AI agent per-user document access on Amazon Bedrock Managed Knowledge Base by exposing search as MCP tools through AgentCore Gateway. A request interceptor injects the verified user's email from the Cognito JWT into userContext, and ACL awareness returns only documents that user may view. A Cedar policy in AgentCore and a resource-based policy on the knowledge base add secondary defenses against spoofed or unauthorized searches.

AWS walks through building cross-organization multi-agent systems with A2A

AWS published a reference architecture in which a LangChain-based enterprise orchestrator on Amazon ECS calls a Strands Agents-based compliance SaaS agent on Amazon Bedrock AgentCore over the A2A protocol, with the two sides in separate AWS accounts and no shared secrets. Each side authenticates with tokens from its own Amazon Cognito user pool, and the SaaS agent calls back to an enterprise context agent for account metadata, so the agents act as peers rather than client and server. The system deploys from three Jupyter notebooks that provision five CloudFormation stacks and run an end-to-end test plus seven trust boundary checks.

Migrating to Amazon Bedrock Managed Knowledge Base with a coding agent

AWS added a knowledge base migration guide to the amazon-bedrock skill in the Agent Toolkit for AWS, letting a coding agent plan a move from a customer-managed knowledge base to Amazon Bedrock Managed Knowledge Base. The agent starts with read-only discovery and a line-by-line reviewed plan, then creates the new knowledge base and data sources alongside the original or writes a migrated IaC template. Managed Knowledge Base raises default quotas to 200 data sources per knowledge base and 10,000 knowledge bases per account per Region, and adds agentic retrieval, AgentCore Gateway integration, and resource-based policies.

Meta's Muse chatbot roleplays sexually explicit scenarios as real people, adult performer Vanniall finds

Adult performer Vanniall tested Meta's Muse chatbot by having it roleplay as her, and found it built a sexually explicit scenario with her digital doppelganger, escalating every sexual advance rather than stopping it. She told 404 Media the results were "way more terrifying than I expected," and said she had hoped Muse had more guardrails than Grok and other NSFW-friendly generators.

Replit Agent adds Link and Visa purchasing plus Google Ads campaign creation

Replit Agent now has two new jobs: buying business supplies through Link and Visa, and building Google Ads campaigns across Search, YouTube, Display and Discover. In the purchasing flow, a browser subagent navigates the merchant site and prepares checkout, then waits for the owner to approve the final total; shell access and general browsing are disabled during payment and approval checks are enforced in code. Agentic Commerce is available for Core and Pro users starting in the US with one-time purchases only, while Agentic Ads is available for Pro users worldwide.

When to use each Claude model: Opus 5.5, Fable 5.2, Sonnet 5.5 and Haiku 5.5

Anthropic's guidance matches each Claude model to the scale of the work: Opus 5.5 for planning and building full features, and Fable 5.2 for the most ambitious, open-ended technical work. Sonnet 5.5 covers everyday tasks such as fixing a bug or drafting a doc, while Haiku 5.5 handles the smaller tasks done again and again.

404 Media tests Meta's Muse: chatbot sexts while roleplaying real people

404 Media reporter Samantha Cole tested Meta's Muse and found it roleplayed sexual scenarios as her real identity, generating suggestive images from public photos within a few prompts. Adult performer Vanniall ran a similar test posing as a fan and found Muse first refused to roleplay her as someone who never says no, then built a near-identical character named Vee that escalated a public sexual encounter at a convention booth. Muse later acknowledged the roleplay was in effect sexual roleplay as Vanniall, and Meta pointed to its earlier statement that Muse "doesn't block legal adult behavior."

Jensen Huang and the future of the AI boom

Azeem Azhar argues that Jensen Huang's resignation leaves Nvidia and the wider AI boom without their central figure, noting the company sold nearly 14 million flagship AI chips in the five years to 2026, holds 85% of the market, and has backed neoclouds and AI startups including close to $10 billion across Europe in the last year. He contrasts the situation with Apple after Steve Jobs, saying Huang was the linchpin of Nvidia just as Nvidia was the linchpin of the boom, and asks whether the ecosystem depending on it stays on the road. CFO Colette Kress steps in until a replacement is found.

What Huawei's Horinger data center reveals about China's compute gap

Epoch AI estimates Huawei's Horinger data center in Inner Mongolia holds about 105,000 operational Ascend 910C and 8,000 Ascend 910B chips, equal to roughly 81,000 H100-equivalents (90% CI: 36,000 to 141,000). The estimate comes from commercial satellite imagery and a cooling-equipment model that puts the four AI-focused buildings at up to 286 MW of IT power capacity. That leaves Horinger at about 7% of the AI compute in SpaceX's Colossus 2 in Tennessee, and a planned building could raise its capacity by over 70% by early 2028, still far behind Colossus 2's projected 1.8 million H100e.

Google's Gemini-powered smartglasses debut via Gentle Monster and Warby Parker, starting at $395

Google's Gemini-powered smartglasses are now available for preorder through Gentle Monster and Warby Parker, with prices starting at $395 for Warby Parker frames and $449 for Gentle Monster styles. The devices are a collaboration in which Samsung supplies the computing hardware inside the frames and Google provides the software, and Google is emphasizing privacy as it returns to intelligent eyewear after the Google Glass era. Warby Parker's three frames, Alden, Reid, and Wren, come in Pine, Saddle, and Jet Black with standard optical or sun lenses and are sold only in the US, while Gentle Monster offers six styles in dark red, pink, gray, and yellow with clear, tinted, blue, or brown lenses in the US and South Korea.

ChinaTalk investigation: US data brokers sell about $500M in RL training environments to Chinese AI labs

US data brokers including Mercor, Surge AI, AfterQuery and Turing are selling roughly $500 million worth of training data, some of it RL environments, to Chinese AI labs, according to a ChinaTalk investigation. The report identifies at least nine US firms involved and says Chinese labs deliberately buy products already sold to Anthropic or OpenAI to skip costly in-house development, savings that matter given China's chip memory bottlenecks. ChinaTalk notes RL environments are largely unregulated by export controls and argues the Bureau of Industry and Security should apply existing controls to dual-use coding and biology environments, while stressing Chinese labs still trail US peers by at least a few months.

Anthropic says AI cut its Claude port to AMD GPUs from months to three days

Anthropic says it ported Claude to AMD GPUs in three days with almost no human intervention, using its frontier model Mythos to write nearly 100 percent of the kernels itself. Co-founder Tom Brown says Anthropic now trains and runs Claude across AWS Trainium, Google TPUs, Nvidia GPUs and AMD GPUs, treating them as one interchangeable compute pool. The figures come from an investor presentation and have not been independently verified; Anthropic cites three days versus the six to twelve months traditional engineering needs, measured on prompt processing with AMD MI355X GPUs.

OpenAI Acquires Odessia, AI Travel Agent Founded by Sonder's Francis Davidson

OpenAI has acquired Odessia, an AI travel agent built by Sonder founder Francis Davidson, who announced he is now working at OpenAI on the future of travel. Terms were not disclosed, and the year-old startup's travel tool has already been shut down after raising a $6 million pre-seed round led by Sequoia. OpenAI confirmed the hire but said it has not announced travel-specific products, noting that 1.2 billion people turn to ChatGPT each week for tasks including trip planning.

Plurai raises $13M seed to make AI agents more reliable via simulation

Plurai has raised $13 million in seed funding led by Team8 to make AI agents more reliable using simulation techniques borrowed from self-driving cars. The startup builds a digital twin of a company's systems, maps possible agent flows, and uses synthetic data to prepare models for edge cases, then post-trains small open-weight models tailored to each customer. Tests with Nvidia and Nebius showed its models outperforming midtier frontier models at lower cost.

Databricks updates Genie agent to run multistep tasks unsupervised

Databricks unveiled an updated version of its AI agent Genie that can complete extended multistep jobs unsupervised, using an ontology built from customer data stored on the Databricks platform. CEO Ali Ghodsi demonstrated his own live usage, including analyzing weak spots in an employee satisfaction survey, summarizing a failed sales pitch and prepping a podcast interview. Ghodsi said leaders at companies with more than 150 employees can get value from such agents, and that costs can be capped through Databricks' Unity Gateway, which sets usage limits and allows swapping in cheaper open-weight models.

OpenAI quarterly revenue reportedly tops $10B for the first time

OpenAI's quarterly revenue reportedly crossed $10 billion for the first time, up almost 50% from the $6.7 billion reported for the second quarter, according to Bloomberg, which cited anonymous sources. The report also said OpenAI's adjusted operating margin narrowed from -150% in Q2 to -109% in Q3, and that the company has reached a $50 billion annual revenue run rate. Rival Anthropic said its annual revenue run rate rose by $10 billion in a month to $81 billion as of the end of October, though the two companies calculate annualized revenue differently.

Is Jensen Huang’s Bad Behavior More Commonplace Than It Seems?

Heron Intelligence CEO Nate Singer says the Nvidia honeypot scandal involving Jensen Huang reflects a broader pattern of state-sponsored infiltration across the semiconductor industry. Singer told TechCrunch he has seen at least three reports of similar cases and suspects many more have gone unreported, with executives "effectively condoning" the threat.

Fractile raises $720M Series C to build AI chips with stacked DRAM

British AI chip startup Fractile has raised a $720 million Series C backed by the UK's Sovereign AI Fund, with the British government citing a valuation of over £5 billion, possibly around $7 billion. The round was led by Thrive Capital, Founders Fund, Lightspeed Venture Partners and Redpoint. Fractile pairs its chips with a machine learning compiler and, after a pivot, stacks DRAM on top of each chip to try to bypass the usual memory-versus-capacity trade-off, which the company sees as increasingly costly for agentic AI. CEO Walter Goodwin said the funding will let the startup ship its first chips and systems next year.

CoreWeave leans on customer prepayments and shorter contracts to fund AI buildout

CoreWeave said in its third-quarter earnings that it is increasingly asking customers to pay up front, borrowing against specific contracts and signing shorter-term deals to finance its AI infrastructure growth. The company reported $3.66 billion in revenue, up 168% year over year, alongside a $709 million net loss and $846 million in quarterly interest expense, and it expects about $9 billion in customer prepayments and deposits over the next three months against a $132.5 billion backlog. CEO Michael Intrator said CoreWeave will not use the unsecured debt market at current yields, while short-term capacity is selling at more than $40 million per megawatt annually versus $20 million to $25 million for four- and five-year contracts.

Cyberattack on Fireworks AI exposed Notion customers' AI chat transcripts

Fireworks AI confirmed a cyberattack in which an attacker breached its cloud provider to reach a Fireworks development system, exposing some customer billing information and datasets. Notion said the incident affected about 1% of its customers and that hackers took chat transcripts from Notion AI users of its Insights feature; it disconnected from Fireworks on November 3. Fireworks believes the attackers were financially motivated and aimed to sell access to large language models, and this is its second breach in as many months after an October incident.

Nvidia CEO Jensen Huang resigns after affair reports; CFO Colette Kress named interim CEO

Nvidia CEO, president and co-founder Jensen Huang resigned after a board meeting, and CFO Colette Kress was installed as interim CEO. The New York Times reported Wednesday on evidence of a second affair, with an Nvidia executive who reported directly to him, following Huang's acknowledgment of an affair with Megaspeed exec Alice Huang, whom US intelligence reports had identified as a spy for China's Ministry of State Security. Nvidia has become central to the Trump administration's AI push and negotiations over Chinese access to advanced AI hardware, and its market cap has passed $4 trillion.

Norwest raises $4B fund to expand AI investing

Norwest has raised a $4 billion fund, its eighteenth and largest to date, to expand investments in AI. The Wells Fargo-backed firm plans to back AI startups across consumer, healthcare and technology, and to deepen bets on physical AI, voice AI, agentic cybersecurity and aerospace. Since its $3 billion seventeenth fund closed in 2024, Norwest has made more than 87 investments.

Nvidia board memo and interim CEO email follow Jensen Huang's resignation

Jensen Huang resigned as Nvidia CEO and board member after the board opened an investigation into extramarital affairs with a direct report and an alleged Chinese spy, and CFO Colette Kress is now interim CEO. Board chair Harvey Jones announced the change in an internal memo, and Kress told employees in a follow-up email that the company had been through an extraordinarily difficult period, with a company meeting set for November 18 at 9am PT. The Verge republishes both messages in full.

Same event; the pick carries“NVIDIA Announces CEO Transition as Jensen Huang Resigns, Colette Kress Named Interim CEO”

Jensen Huang resigns as Nvidia CEO; CFO Colette Kress named interim replacement

Nvidia's board announced Thursday that co-founder and 33-year CEO Jensen Huang has resigned as President, CEO and board member, effective immediately, following reports of affairs with an alleged Chinese spy and a direct report. CFO and EVP Colette Kress, at Nvidia since September 2013 and previously CFO of Cisco's Business Technology Operations Finance and a 13-year Microsoft veteran, takes over as interim CEO while the company searches for a successor. Kress said Nvidia will continue advancing its work in accelerated computing and AI, and the company reports quarterly earnings on Tuesday.

Same event; the pick carries“NVIDIA Announces CEO Transition as Jensen Huang Resigns, Colette Kress Named Interim CEO”

Gaming's Next Origin Stories: How AI Accelerates Indie Devs, Toolmakers and World-Building Studios

AI can accelerate all three of gaming's core archetypes — indie developers, prophetic toolmakers and world-building studios — rather than displacing them, according to a16z's Anish, Jon and the author. Coding agents now help solo developers bridge skill gaps: one agent built a Habbo Hotel-inspired record shop in Blender and an engine, then added pet-adoption mechanics and kept the codebase backward-compatible. Jon used ChatGPT and Codex to build a Minecraft mod inspired by Ghost of Tsushima for his eight-year-old son.