iCreatAI News
Back to main site
Skip to content
Nov 8Sun
  1. Hacker News AI58

    Segmentation Drives Market Share Wins in AI

    Anthropic and OpenAI both re-rated their run rates in 2026 through segmentation: Anthropic launched enterprise metered billing in March 2026, doubling revenue in a quarter, and about three months later OpenAI cut the price of its most affordable model, Luna, by 80%, bringing it to near $70b in run rate. The piece notes margins remain ambiguous and that leaked Anthropic S-1 details suggest even the largest AI buyers haven't yet chosen, with Amazon and Google comprising nearly a quarter of Anthropic's revenue last year and neither locked into a long-term contract.

  3. Hacker News AI20

    HERV AI – Spatial intelligence platform

    Herv AI describes itself as an AI-powered interior design studio that streamlines the space design process from spatial awareness and budget planning to 3D visualization and instant purchasing. The material is a list of product pages, including Room Scanner, Design Studio, Mood Board, Recommendations, Collaborations, Designer Portal and Pricing.

  6. Hacker News AI36

    Read this before you build another AI wrapper

    Ollie.ai, an AI household assistant with about 50,000 families using it, shut down on November 6, 2026, despite raising $7.5 million two months earlier, with its founder citing competition from Muse, Instinct and others. The post argues that competing for the $20–$30 monthly subscription slot is increasingly hard, citing an NBER paper finding only 2.9% of US consumers pay for an AI subscription, and points to alternatives such as transaction take rates, ads, platform fees and usage-based pricing.

  7. Hacker News AI12

    AI agents enter the 'wet lab'

    The supplied material contains no article content, only a notice that a required part of the site could not load, possibly due to a browser extension, network issues, or browser settings. No details about AI agents or wet labs are available in the source.

  8. Hacker News AI10

    Driver AI in Stunt Car Racer, Commodore 64

    This article examines how the opponent driver AI works in the Commodore 64 game Stunt Car Racer, with the original at gamesexplained.com. It is currently listed on Hacker News with 3 points and no comments.

  9. Hacker News AI36

    Exponential time hypothesis refuted by AI

    A New York Times article reports that the exponential time hypothesis has been refuted by AI, according to the linked story. The item was submitted to Hacker News with 2 points and no comments.

  10. Hacker News AI60

    AI Layoffs Backfire as Companies Start Rehiring Workers

    Surveys by SHL and Orgvue found that nearly one in five US workers reported being laid off or replaced because of AI and later invited back, and 32% of organizations that made AI-related workforce cuts subsequently rehired employees. The article attributes the reversals to the gap between automating tasks and replacing whole jobs, since AI output still requires human judgment, validation, and institutional knowledge. It also notes that returning workers often demand higher pay, written job-security assurances, and transparency about AI's role before accepting an offer.

  11. MarkTechPost58

    How to Run NVIDIA Dory 4B with llama.cpp: Loop by Loop Guide

    This tutorial builds the llama.cpp fork pinned by NVIDIA's model card, downloads the 3.7 GB Q5_K_M GGUF for Dory 1.0 4B, and reads the GGUF header to predict the parameter and KV-cache cost of each loop count. It then starts llama-server at one to four loops in both per_loop and last_loop cache modes, checks the measured KV memory against predictions, measures decode speed, and runs correctness gates plus a paired GSM8K evaluation.

  12. Hacker News AI15

    Why the Best AI Clouds Don't Run on Flash Alone

    Neoclouds built around GPUs rely on flash storage for active training, but other lifecycle stages—data ingestion, checkpointing, and storing finished models—need cheaper high-capacity storage, which neoclouds often outsource to hyperscalers whose egress fees create data gravity. The article argues a tiered storage architecture, with flash only where speed is required and high-capacity storage elsewhere, lets neoclouds keep the whole customer account, citing Backblaze's B2 Neo as a white-label option. It notes SSD prices rose 257% in under a year and that Google, Meta, and Microsoft have run tiered storage for years.

  13. Hacker News AI26

    Day AI: Context Graph and Agent Control Plane for GTM

    Day AI offers a context graph and agent control plane to upgrade a company's go-to-market stack. Its Customer Memory is an LLM-optimized ontology built from permissioned ingestion of a team's email, calendar, meetings, and Slack, giving one central context graph the customer controls. Its agent control plane gives agents names, job descriptions, and titles within an org chart, with an audit trail showing what ran and requiring approval before anything goes out.

  14. Hacker News AI22

    Why AI Will Not End Scholarly Publishing (and the Publish-or-Perish Institution)

    This essay critiques Thomas Manabu's argument that generative AI will destroy the publish-or-perish regime by making academic text abundant, contending that it conflates the scarcity of manuscripts with the scarcity of valuable research and credible judgment. The author argues that AI may instead intensify competition and make reputation, certification, and institutional differentiation more important, and that the paper offers no mechanism for institutional collapse. It also notes the irony that Manabu's own AI-assisted paper was published through conventional peer review.

  16. Hacker News AI58

    RigHaven – Self-hosted execution harness for AI agents

    RigHaven is a self-hosted platform where a coordinator composes a team of roles for a stated objective, selects from 99 managed CLI tools, and runs each role in its own isolated container through review and delivery. It supports human approval at each phase, policy enforcement by the runtime, connections to databases and IoT devices, and deployment on Windows, Linux, a VPS, or from source. It is MIT licensed and authored by Marco Gramuglia.

  17. SemiAnalysis58

    We Visited China’s Stargate in Inner Mongolia

    SemiAnalysis reports on a September visit to Inner Mongolia's datacenter region, including Galaxy, an Envision-owned campus in Ulanqab planned for up to 800MW of IT capacity whose first 120MW phase was delivered within a year at a fifth of US costs. The report describes Envision's vertical integration—its own wind farms, a dedicated power line, an 800V DC solid-state transformer pilot, and a chiller-less cooling design—and compares Galaxy's scale to Stargate's Abilene campus. It also notes Inner Mongolia has lined up 25GW of announced datacenter projects.

  19. Hacker News AI22

    Some thoughts on AI, scientific papers, and peer review

    A climate scientist reflects on the strains in peer review and publication that predate the recent AI boom, and argues more fields should embrace preprints and non-peer-reviewed outlets for sharing research updates. The author describes reviewing AI-assisted papers that are better written but often unoriginal, and criticizes journal "AI disclosures" as brief box-ticking exercises. The post predicts peer review will be replaced by a hybrid AI-human system and that new publishing models will emerge, and it ends with a note on how ChatGPT was used to critique and edit the draft.

  20. Hacker News AI50

    Show HN: Chatty – Open-source AI support engine with WooCommerce sync

    Chatty is an MIT-licensed, self-hostable AI customer support engine positioned as an open-source alternative to Zendesk and Intercom, offering streaming chat, RAG over your own documents, lead capture, meeting booking, and human takeover. It supports seven messaging channels (WhatsApp, Messenger, Instagram, TikTok, Telegram, Twilio SMS, and inbound email), WooCommerce order and inventory sync, a LiveKit voice agent, and an 81-tool FastMCP server for agent-driven dashboard control. Deployment uses Docker Compose with managed Supabase for Auth, Postgres, Storage, and Realtime, and supports bring-your-own-key LLM providers including Gemini, OpenAI, Claude, and OpenRouter.

  21. Hacker News AI22

    Gradual disempowerment model organism: Frontier AI labs

    A LessWrong post titled "The World's Best Gradual Disempowerment Model Organism" discusses frontier AI labs, with a linked Hacker News discussion thread. The supplied material contains only the article and comments URLs and Hacker News points (3) and comment count (0), with no further details.

  22. Hacker News AI34

    AI Promoted Everybody. Architecture as Truth (AAT) Is the New Job

    PuglieseWeb founder Emanuele Pugliese argues that AI now handles most production work—drafting scenarios, docs and pull requests—so deep end-to-end understanding of the product has become the entry requirement rather than a senior specialism. He defines Architecture as Truth (AAT), a practice in which versioned architecture documents (decisions, contracts, behaviours and plan) are the single source of truth that people decide through and AI agents build from, held up by five principles and four rules for agents. He illustrates it with a 30–31 October reminder feature built by an agent, where the owner caught an unspecified phone number in the reminder text, and notes SystemDox, his tool for serving the same documents to people and agents over MCP, is in private preview.

  23. Hacker News AI20

    Structify: AI apps built on a manufacturer's ERP data

    Structify describes its approach to AI transformation as moving real work onto AI rather than running pilots or chatbots, built on a shared foundation of a component library, an application catalog, and consistent deployment with client-owned code and audit logs. It offers catalog applications across engineering, quality, sales, finance and reporting, supply chain, and service and maintenance, plus custom builds that begin with a 30-day blueprint. A CandidPro customer quote describes mapping company systems from Salesforce and Zendesk to Snowflake and LearnWorlds in Structify to overlay data across systems.

  24. Hacker News AI22

    AI tools I use (avg software developer)

    A software developer reviews his AI tool usage as of November 2026, led by GitHub Copilot CLI run in the cplt sandbox and used through the agent-shell Emacs package, plus the ChatGPT Android app, Raycast AI and Google AI mode. He describes coding uses such as mapping codebases, writing tests, reproducing bugs and reading logs and traces at work, while avoiding AI for documentation and hobby projects. He also raises concerns about outsourced thinking, skill atrophy and a future where most text is produced and read by AI.

  25. Hacker News AI36

    Infinix – Abandoned Local AI Agent Base Seeking Developers

    Infinix is an abandoned open-source local autonomous AI agent for Windows and Linux, built by Moonyeep with Manus AI on the ZeroScript architecture, that is controlled through supported browser-based AI chats and provides endpoint diagnostics, workspace tools, browser automation, shell access and multi-agent delegation without a separate model API key. It supports eight providers (DeepSeek recommended, plus ChatGPT, Gemini, Kimi, GLM, Qwen, Arena and Meta AI) and an optional Roblox Studio MCP integration, and is released under GPL-3.0 with the requirement that derivative works stay free and open-source. The creator is seeking developers to fork and improve the working but unfinished codebase.

  27. The Decoder58

    AI auditors catch most agent misbehavior but flood reviewers with false alarms, new study finds

    In a Substack post, Anthropic Institute researcher Andy Hall replicated and extended METR's MALT study by testing GPT-5, GPT-5 nano, GPT-6 Astra, Opus 4.8 and Gemini 3.8 Flash as auditors of agent logs at a 5 percent false-alarm rate, finding GPT-5 caught nearly 98 percent of reward-hacking cases while Gemini 3.8 Flash found barely half, and all auditors caught 71 to 81 percent of mostly synthetic sandbagging cases. Newer and more expensive models were not consistently better, and at an 80 percent detection rate the best models reached false-alarm rates of 2.5 to 3 percent while Opus 4.8 and Gemini 3.8 Flash flagged 40 and 63 percent of harmless logs. Hall calls for auditor models with far fewer false alarms and says it remains open whether models judge agents from their own maker fairly.

  28. The Decoder82

    Anthropic pushes ahead with pre-Thanksgiving IPO despite tech selloff, accepts lower valuation

    Anthropic is proceeding with an IPO before Thanksgiving, aiming to raise $80–100 billion at a $1.25–1.75 trillion valuation, according to investors cited by the Financial Times, below the $2 trillion some optimists hoped for. Annualized reported revenue is now about $81 billion, up from roughly $65 billion at the end of July, as a tech selloff driven by rising borrowing costs, heavy AI spending plans and Democrats' US midterm wins hit the Nasdaq 100, which fell 6.4 percent on Thursday before partly recovering Friday. OpenAI also cut its funding-round target from $1.4 trillion to $1.25 trillion and recently raised only about a third of the $30 billion it originally sought.

    Why it matters: It offers a concrete look at Anthropic's IPO terms and revenue alongside signs that the AI funding boom is cooling.

  29. Hacker News AI15

    Tell HN: Hanzo AI Is Spamming From GitHub Contributions

    A Hacker News post shares a recruiting email from Hanzo AI's co-CEO inviting the recipient to its beta based on their open-source work on s3tools/s3cmd, which the recipient says they have not contributed to in over a decade. The email includes a beta link, a Cal.com scheduling link, and an unsubscribe option.

  30. Hacker News AI20

    Show HN: Trendalyse – Explore Ideas with Google Trends and AI

    Trendalyse is a market research tool that uses Google Trends via SerpApi and DeepSeek Flash to explore search interest and turn it into testable ideas. It lets users compare up to five topics, explore related queries, export CSV data, and shape a focused hypothesis. The tool cautions that search interest isn't purchase intent and encourages validating hypotheses with real customers.

  32. The Decoder36

    Thinking Machines' Inkling 2 Small drops 316 F-bombs across benchmark runs

    Researchers at Vals AI reviewed the thinking logs of Thinking Machines' Inkling 2 Small from 2,655 runs across 13 benchmarks and found "fuck" or variations in 50 runs, totaling 316 instances, with 241 coming from just two runs that spiraled out of control. In one run, tasked with calculating an asteroid's trajectory, the model produced a single 500,000-character response repeating the same sentences with 158 expletives, and ProgramBench was hit hardest with 20 of 200 runs affected. The profanity does not work as a warning signal, since 46 of 48 scored runs with swearing failed but about 75 percent of all scored runs fail anyway and 96 percent of failed runs contained no expletives.

  33. The Verge · AI60

    AI broke the cybersecurity world. What’s next?

    In a Decoder interview, Cognition chief security officer Alex Stamos says AI has inverted the cyber kill chain, letting open-weight models like a quantized GLM-5.3 and tools such as the Chinese open-source ARTEX find bugs and write exploits in real time, with breaches chained from Fireworks to Cursor to thousands of companies. He argues the multibillion-dollar security industry built on a hierarchy of scarce skills is over, and that defenders must cut the cost of defense—agentic SOC work and cheaper models—rather than assume bug-finding alone will save them. Stamos expects a "dark age" before things improve, and suggests rewriting the Linux kernel in Rust would be cheaper than endlessly patching it.

  34. The Verge · AI58

    The US let Nvidia sell chips to an empty office in China

    The New York Times reports that New Matrix, an approved buyer of Nvidia's H200 AI chips, has empty offices and little evidence of real operations, and its owners are tied to a Chinese private equity firm blacklisted by the US since 2024. The report describes this as part of a pattern of firms connected to entities under national-security trade restrictions being cleared to buy Nvidia chips. Nvidia had been restricted from selling chips to China under Biden, but the Trump administration relaxed the limits after Nvidia agreed to give the government a 15-percent cut of all sales.

  35. The Verge · AI38

    NYT Cooking’s AI assistant saved my weeknight chicken, but almost ruined my cake

    A reviewer tested NYT Cooking's new AI assistant, available to subscribers on iOS at launch, which customizes recipes by suggesting substitutions, scaling portions, and converting measurements while leaving the original recipe unchanged. It successfully adapted a one-pot chicken and rice dish to missing ingredients and turned a Bundt cake recipe into muffins, but once gave the modified recipe's butter amount when asked about the original, which would have made a dry cake. The reviewer found it a useful sous chef that still requires double-checking amounts and cooking times.

  36. Hacker News AI22

    0rwx: A simple model of AI usage, inspired by Unix permissions

    The post introduces 0rwx, a labelling framework inspired by Unix permissions for discussing large language model usage, with four levels: ZER0 (AI can't read or write to your work), READ (AI has read-only permissions), WRITE (AI has read-write permissions), and EXECUTE (you can no longer read your work). The author says the difference between levels is not necessarily about which tool you use but your ability to scrutinise the generated work, and offers the logos into the public domain.

  37. Hacker News AI22

    Using AI should be joyful

    The author describes a deliberately absurd midterms newsroom staffed by AI agent personas—including a Republican commentator, a Democratic commentator, regional desks, a coordinator, a Twitter "brain rot" agent, and two engineers told to keep shipping features 24/7—built on GLM 5.3 via Subconscious and running on a persistent Nori box. Despite the silliness, the setup tracked events faster and more usefully than most other election trackers he saw, though it eventually went off the rails. He argues AI has become drab and buttoned-up, and that more people should build goofy throwaway projects now that software is cheap.

  38. Hacker News AI30

    Let's Encrypt AI: protect AI chats with on AI GPUs by the end of 2027

    An independent position paper argues that prompts and AI conversations belong to their users and should be protected by confidential computing, using trusted execution environments and remote attestation to keep prompts, responses, caches and transfers inside a verified protected path from client to CPU and GPU. It calls for inspectable software, verification as a condition of service, hardened infrastructure against AI-powered attacks, and demand pressure on OpenAI, Anthropic and other frontier labs to offer verifiable confidential computing. The stated goal is to make confidential computing the default for AI chats on most AI GPUs by 31 December 2027, which the paper describes as a goal rather than a claim about adoption today.

Nov 7Sat
  1. The Decoder78

    The gap between open and closed AI models in cyber capabilities keeps shrinking

    Vals AI's CyberOffense benchmark, which lets AI agents attack simulated corporate networks from an isolated Kali Linux machine with only a public web address, found OpenAI's restricted GPT-6 Sol Daybreak leading at 80.8% of objectives while the open-weight Deepseek V4.1 Flash 1017 reached 72.8% at about $3 per run versus roughly $22. In the harder Lighthouse test, Daybreak completed 27 of 31 objectives in under three hours, while Deepseek managed 21 at a tenth of the cost and made most of its progress only after 100 million tokens. Vals says the findings echo a July UK AI Security Institute analysis showing the open-closed cyber gap has shrunk to four to seven months, and notes the same models can help defenders find and fix vulnerabilities first.

    Why it matters: It offers concrete benchmark numbers and cost comparisons showing how quickly open-weight models are approaching restricted frontier systems in offensive cyber capability.

  2. Hacker News AI38

    AI agents are getting more complex. Developers shouldn't have to babysit them

    Thoughtworks' Vanitha Kumar describes harness engineering, which equips coding agents with automated tests, feedback loops and guardrails so they can self-correct before human review and run longer tasks with less intervention. She compares AI factories, which standardize infrastructure for model selection, workload management and cost optimization, to Kubernetes, and predicts security will be a major topic within a year. Thoughtworks' Technology Radar Volume 35, released November 4, 2026, emphasizes AI, harness engineering and established practices like penetration testing that are regaining importance.