{
  "schema": "hangingcontext.desk/1",
  "type": "edition",
  "id": "2026-11-18T00",
  "title": "2026-11-18 00:00 UTC",
  "generated_at": "2026-11-22T12:37:14Z",
  "story_count": 27,
  "stories": [
    {
      "slug": "qualifying-offer-split-decision",
      "url": "https://hangingcontext.com/stories/2026-11-18/qualifying-offer-split-decision/",
      "json": "https://hangingcontext.com/stories/2026-11-18/qualifying-offer-split-decision/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/qualifying-offer-split-decision/index.md",
      "headline": "One catcher took the $23.15 million. Four free agents bet they can beat it",
      "dek": "Ryan Jeffers stayed with the Twins on a $23.15 million qualifying offer while Morejon, Rogers, Suzuki and Lowe turned theirs down. The White Sox, meanwhile, paid $52.5 million for certainty.",
      "newsroom": "sports",
      "beat": null,
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:51:35Z",
      "trust": "confirmed",
      "source_count": 6,
      "cited_manifest_ids": [
        "1794960276796741275",
        "1794951376576569629",
        "1794951364215569612",
        "1794948979027506611",
        "1794948935300506550",
        "1794950459203561025"
      ]
    },
    {
      "slug": "allocators-retest-three-orthodoxies",
      "url": "https://hangingcontext.com/stories/2026-11-18/allocators-retest-three-orthodoxies/",
      "json": "https://hangingcontext.com/stories/2026-11-18/allocators-retest-three-orthodoxies/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/allocators-retest-three-orthodoxies/index.md",
      "headline": "After October's turbulence, allocators are re-testing three old answers",
      "dek": "Cambridge Associates says the case for equity long/short funds survives only where managers show real stock-picking skill. RBC BlueBay argues today's securitized credit is not the pre-crisis version. Meketa says the risks no longer sit in separate boxes.",
      "newsroom": "finance-investing",
      "beat": null,
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:51:31Z",
      "trust": "confirmed",
      "source_count": 3,
      "cited_manifest_ids": [
        "1794952655481577973",
        "1794945274046483356",
        "1794945723950485328"
      ]
    },
    {
      "slug": "verified-fixes-not-findings",
      "url": "https://hangingcontext.com/stories/2026-11-18/verified-fixes-not-findings/",
      "json": "https://hangingcontext.com/stories/2026-11-18/verified-fixes-not-findings/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/verified-fixes-not-findings/index.md",
      "headline": "AI finds the bug in seconds. Proving the fix is the new bottleneck",
      "dek": "A Microsoft pilot shipped verified fixes, a migration test needed an independent verifier, and enterprise buyers want one testing platform. Verification is where agent coding now stalls.",
      "newsroom": "artificial-intelligence",
      "beat": "developers",
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:51:27Z",
      "trust": "confirmed",
      "source_count": 3,
      "cited_manifest_ids": [
        "1794956581380602423",
        "1794943996930468648",
        "1794944556734477076"
      ]
    },
    {
      "slug": "developer-workflow-rebuilt-for-agents",
      "url": "https://hangingcontext.com/stories/2026-11-18/developer-workflow-rebuilt-for-agents/",
      "json": "https://hangingcontext.com/stories/2026-11-18/developer-workflow-rebuilt-for-agents/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/developer-workflow-rebuilt-for-agents/index.md",
      "headline": "The developer workflow is being rebuilt so agents can keep up",
      "dek": "GitHub's session protocol, Google AI Studio's instant Android builder and a filesystem that cuts checkouts from 36 minutes to seconds. The dev loop is being rebuilt for agents.",
      "newsroom": "artificial-intelligence",
      "beat": "developers",
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:51:22Z",
      "trust": "confirmed",
      "source_count": 3,
      "cited_manifest_ids": [
        "1794956581380602424",
        "1794947625909496835",
        "1794940142862420183"
      ]
    },
    {
      "slug": "agents-that-do-the-task",
      "url": "https://hangingcontext.com/stories/2026-11-18/agents-that-do-the-task/",
      "json": "https://hangingcontext.com/stories/2026-11-18/agents-that-do-the-task/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/agents-that-do-the-task/index.md",
      "headline": "The personal agent stops answering and starts doing the errand",
      "dek": "Gemini's Task mode, Muse in Australia and Gemini 4 Hydrogen for robotics all ship the same idea: the agent acts, with your approval, and tells the business it is an AI.",
      "newsroom": "artificial-intelligence",
      "beat": "models-labs",
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:51:18Z",
      "trust": "confirmed",
      "source_count": 3,
      "cited_manifest_ids": [
        "1794938214268388705",
        "1794944231953470818",
        "1794944785879478645"
      ]
    },
    {
      "slug": "goldman-bets-against-consensus-2027",
      "url": "https://hangingcontext.com/stories/2026-11-18/goldman-bets-against-consensus-2027/",
      "json": "https://hangingcontext.com/stories/2026-11-18/goldman-bets-against-consensus-2027/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/goldman-bets-against-consensus-2027/index.md",
      "headline": "Goldman is betting against the consensus on 2027 — twice",
      "dek": "The bank's 2027 outlooks put US growth above the 2.2% consensus and UK growth above 1.2%, driven by AI investment. The same outlooks expect rate hikes before any cuts.",
      "newsroom": "finance-investing",
      "beat": null,
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:51:13Z",
      "trust": "confirmed",
      "source_count": 4,
      "cited_manifest_ids": [
        "1794952474756576642",
        "1794952474756576641",
        "1794937185679368253",
        "1794955670633597831"
      ]
    },
    {
      "slug": "control-is-the-pitch",
      "url": "https://hangingcontext.com/stories/2026-11-18/control-is-the-pitch/",
      "json": "https://hangingcontext.com/stories/2026-11-18/control-is-the-pitch/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/control-is-the-pitch/index.md",
      "headline": "The consumer AI pitch this week is control, not capability",
      "dek": "Adobe promises choice over when to use AI, Google gives away avatars restricted to your own likeness, and Muse asks before it acts. Control is the pitch now.",
      "newsroom": "artificial-intelligence",
      "beat": "models-labs",
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:51:09Z",
      "trust": "confirmed",
      "source_count": 3,
      "cited_manifest_ids": [
        "1794958882940735148",
        "1794936072521295452",
        "1794944231953470818"
      ]
    },
    {
      "slug": "inference-splits-for-agent-traffic",
      "url": "https://hangingcontext.com/stories/2026-11-18/inference-splits-for-agent-traffic/",
      "json": "https://hangingcontext.com/stories/2026-11-18/inference-splits-for-agent-traffic/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/inference-splits-for-agent-traffic/index.md",
      "headline": "Agents re-send everything on every call. The inference stack just split in two to cope",
      "dek": "Cerebras splits prefill from decode, AMD caches the history agents keep re-sending, and attention costs dominate long context. The inference stack is being rebuilt around agent traffic.",
      "newsroom": "artificial-intelligence",
      "beat": "infrastructure",
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:51:04Z",
      "trust": "confirmed",
      "source_count": 3,
      "cited_manifest_ids": [
        "1794943772386467266",
        "1794932752465071794",
        "1794938513870392321"
      ]
    },
    {
      "slug": "resistant-infections-new-counterattack",
      "url": "https://hangingcontext.com/stories/2026-11-18/resistant-infections-new-counterattack/",
      "json": "https://hangingcontext.com/stories/2026-11-18/resistant-infections-new-counterattack/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/resistant-infections-new-counterattack/index.md",
      "headline": "The bugs are outrunning the drugs. The counterattack is phages, maps and vaccines",
      "dek": "A phage cocktail that covers most drug-resistant Klebsiella, a new cholera phage, surging drug-resistant TB in Brazil and a returning pneumococcal strain in Catalonia.",
      "newsroom": "health-biotech",
      "beat": null,
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:50:59Z",
      "trust": "confirmed",
      "source_count": 4,
      "cited_manifest_ids": [
        "1794929272793041218",
        "1794949413124511466",
        "1794956379630601545",
        "1794938358482390807"
      ]
    },
    {
      "slug": "credit-funds-ai-buildout",
      "url": "https://hangingcontext.com/stories/2026-11-18/credit-funds-ai-buildout/",
      "json": "https://hangingcontext.com/stories/2026-11-18/credit-funds-ai-buildout/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/credit-funds-ai-buildout/index.md",
      "headline": "Debt, not equity, is now paying for the AI buildout",
      "dek": "Hyperscaler spending is projected at about $3.8 trillion from 2026 through 2028, with credit funding more than half. UBS puts AI capital spending at $1 trillion this year alone. The binding limits are physical and political.",
      "newsroom": "finance-investing",
      "beat": null,
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:50:54Z",
      "trust": "confirmed",
      "source_count": 4,
      "cited_manifest_ids": [
        "1794939608907410709",
        "1794943054305460099",
        "1794945723950485329",
        "1794928267065035639"
      ]
    },
    {
      "slug": "volcanoes-we-cannot-see",
      "url": "https://hangingcontext.com/stories/2026-11-18/volcanoes-we-cannot-see/",
      "json": "https://hangingcontext.com/stories/2026-11-18/volcanoes-we-cannot-see/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/volcanoes-we-cannot-see/index.md",
      "headline": "We can watch a volcano erupt through a fibre-optic cable. Most dangerous volcanoes, we cannot watch at all",
      "dek": "Fibre-optic sensors tracked an Icelandic eruption, a new satellite method sharpens heat maps — and open geodetic data cannot detect magma building under 64% of the most dangerous populated volcanoes.",
      "newsroom": "energy-climate",
      "beat": null,
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:50:49Z",
      "trust": "reported",
      "source_count": 3,
      "cited_manifest_ids": [
        "1794952638984577947",
        "1794936164644306982",
        "1794927341974031574"
      ]
    },
    {
      "slug": "nimh-retires-four-data-sharing-rules",
      "url": "https://hangingcontext.com/stories/2026-11-18/nimh-retires-four-data-sharing-rules/",
      "json": "https://hangingcontext.com/stories/2026-11-18/nimh-retires-four-data-sharing-rules/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/nimh-retires-four-data-sharing-rules/index.md",
      "headline": "NIMH is retiring four of its own data-sharing rules and pointing researchers to one NIH-wide policy",
      "dek": "Effective November 17, the National Institute of Mental Health rescinded its autism and clinical-research data-sharing notices. Applicants now follow the NIH-wide data management policy.",
      "newsroom": "federal-government",
      "beat": null,
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:50:44Z",
      "trust": "reported",
      "source_count": 4,
      "cited_manifest_ids": [
        "1794938610110392959",
        "1794938610110392958",
        "1794932091020062810",
        "1794926283889025263"
      ]
    },
    {
      "slug": "code-mode-cuts-agent-tool-cost",
      "url": "https://hangingcontext.com/stories/2026-11-18/code-mode-cuts-agent-tool-cost/",
      "json": "https://hangingcontext.com/stories/2026-11-18/code-mode-cuts-agent-tool-cost/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/code-mode-cuts-agent-tool-cost/index.md",
      "headline": "Stop calling tools one by one. Code mode cuts the token bill by up to 90 percent",
      "dek": "Three new studies point the same way: how an agent calls tools matters more than which model does the calling. The cheapest wins come from the interface, not the model.",
      "newsroom": "artificial-intelligence",
      "beat": "models-labs",
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:50:39Z",
      "trust": "reported",
      "source_count": 4,
      "cited_manifest_ids": [
        "1794920873496997402",
        "1794920873496997404",
        "1794920873495997391",
        "1794920873495997392"
      ]
    },
    {
      "slug": "rag-agents-evidence-discipline",
      "url": "https://hangingcontext.com/stories/2026-11-18/rag-agents-evidence-discipline/",
      "json": "https://hangingcontext.com/stories/2026-11-18/rag-agents-evidence-discipline/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/rag-agents-evidence-discipline/index.md",
      "headline": "Your RAG agent cites the echo, not the evidence. Four new tests show the fix",
      "dek": "Agent pipelines lose to a plain baseline on claim support, ignore primary evidence when a false claim repeats, and refuse badly when documents conflict. The same batch of papers shows what repairs each failure.",
      "newsroom": "artificial-intelligence",
      "beat": "research",
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:50:35Z",
      "trust": "reported",
      "source_count": 4,
      "cited_manifest_ids": [
        "1794920367140993425",
        "1794920367141993428",
        "1794920367139993411",
        "1794920367139993408"
      ]
    },
    {
      "slug": "judges-miss-cultural-errors",
      "url": "https://hangingcontext.com/stories/2026-11-18/judges-miss-cultural-errors/",
      "json": "https://hangingcontext.com/stories/2026-11-18/judges-miss-cultural-errors/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/judges-miss-cultural-errors/index.md",
      "headline": "The judges cannot see cultural errors, and the safety scores hide it",
      "dek": "Four new evaluations find the same gap from different directions: models stumble on culture and language outside the English-language mainstream, and the tests meant to catch it are not catching it.",
      "newsroom": "artificial-intelligence",
      "beat": "research",
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:50:31Z",
      "trust": "reported",
      "source_count": 4,
      "cited_manifest_ids": [
        "1794921793731004921",
        "1794919918017991444",
        "1794921793731004919",
        "1794921793731004912"
      ]
    },
    {
      "slug": "jailbreaks-find-new-surfaces",
      "url": "https://hangingcontext.com/stories/2026-11-18/jailbreaks-find-new-surfaces/",
      "json": "https://hangingcontext.com/stories/2026-11-18/jailbreaks-find-new-surfaces/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/jailbreaks-find-new-surfaces/index.md",
      "headline": "Jailbreaks keep finding new doors: style, bitstreams, split intent, and sampling",
      "dek": "Four preprints posted this week attack safety from four different directions, and each one shows the current defenses watching the wrong place.",
      "newsroom": "artificial-intelligence",
      "beat": "research",
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:50:26Z",
      "trust": "reported",
      "source_count": 4,
      "cited_manifest_ids": [
        "1794919918018991451",
        "1794919918016991435",
        "1794919918018991452",
        "1794919918018991450"
      ]
    },
    {
      "slug": "smaller-central-banks-write-own-scripts",
      "url": "https://hangingcontext.com/stories/2026-11-18/smaller-central-banks-write-own-scripts/",
      "json": "https://hangingcontext.com/stories/2026-11-18/smaller-central-banks-write-own-scripts/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/smaller-central-banks-write-own-scripts/index.md",
      "headline": "While the big central banks debate, the smaller ones are moving",
      "dek": "The rate cycle is fragmenting. Hungary held, Poland is disinflating, New Zealand's central bank is still tightening, and the ECB is refining how it talks to markets.",
      "newsroom": "finance-investing",
      "beat": null,
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:50:21Z",
      "trust": "confirmed",
      "source_count": 4,
      "cited_manifest_ids": [
        "1794925031595019748",
        "1794919677003991146",
        "1794950826509565707",
        "1794955386090596029"
      ]
    },
    {
      "slug": "fed-writes-crisis-rules-while-calm",
      "url": "https://hangingcontext.com/stories/2026-11-18/fed-writes-crisis-rules-while-calm/",
      "json": "https://hangingcontext.com/stories/2026-11-18/fed-writes-crisis-rules-while-calm/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/fed-writes-crisis-rules-while-calm/index.md",
      "headline": "The Fed is writing the rules for the next Treasury panic while markets are calm",
      "dek": "A Cleveland Fed president argues the central bank should decide in advance when it would step into the $32 trillion Treasury market. New Fed research shows why the plan could fail: banks fear the market reaction to borrowing.",
      "newsroom": "finance-investing",
      "beat": null,
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:50:18Z",
      "trust": "confirmed",
      "source_count": 3,
      "cited_manifest_ids": [
        "1794942929769459585",
        "1794918478534987967",
        "1794929023742040027"
      ]
    },
    {
      "slug": "ai-does-the-science-now",
      "url": "https://hangingcontext.com/stories/2026-11-18/ai-does-the-science-now/",
      "json": "https://hangingcontext.com/stories/2026-11-18/ai-does-the-science-now/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/ai-does-the-science-now/index.md",
      "headline": "AI stops assisting the science and starts doing it",
      "dek": "Isomorphic Labs raised $5 billion to design medicines, a Microsoft diagnosis agent beat human generalists, and one researcher runs the whole pipeline on Claude Code.",
      "newsroom": "artificial-intelligence",
      "beat": "models-labs",
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:50:13Z",
      "trust": "confirmed",
      "source_count": 3,
      "cited_manifest_ids": [
        "1794918063518985879",
        "1794937327889372361",
        "1794943996931468649"
      ]
    },
    {
      "slug": "income-is-back-households-missed-it",
      "url": "https://hangingcontext.com/stories/2026-11-18/income-is-back-households-missed-it/",
      "json": "https://hangingcontext.com/stories/2026-11-18/income-is-back-households-missed-it/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/income-is-back-households-missed-it/index.md",
      "headline": "Bond income is back. Households are still almost all in stocks.",
      "dek": "BlackRock's fixed-income chief argues income now does the heavy lifting in a portfolio, and Vanguard is cutting credit risk while expecting two more rate hikes. The catch: households have barely moved.",
      "newsroom": "finance-investing",
      "beat": null,
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:50:09Z",
      "trust": "confirmed",
      "source_count": 3,
      "cited_manifest_ids": [
        "1794944751790477868",
        "1794917829827967023",
        "1794941062973442371"
      ]
    },
    {
      "slug": "enterprises-buy-agents-not-models",
      "url": "https://hangingcontext.com/stories/2026-11-18/enterprises-buy-agents-not-models/",
      "json": "https://hangingcontext.com/stories/2026-11-18/enterprises-buy-agents-not-models/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/enterprises-buy-agents-not-models/index.md",
      "headline": "Enterprises are buying agents, not models. Governance is what is holding them back",
      "dek": "A Databricks revenue update, a SemiAnalysis spending breakdown, a survey of 150 IT leaders, and a venture firm's infrastructure thesis all point the same way: the buying has started, and the blockers are access, identity, and proof.",
      "newsroom": "artificial-intelligence",
      "beat": "funding-deals",
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:50:04Z",
      "trust": "confirmed",
      "source_count": 4,
      "cited_manifest_ids": [
        "1794917820413966696",
        "1794958272443731745",
        "1794928480391036751",
        "1794949233910510436"
      ]
    },
    {
      "slug": "long-context-memory-squeeze",
      "url": "https://hangingcontext.com/stories/2026-11-18/long-context-memory-squeeze/",
      "json": "https://hangingcontext.com/stories/2026-11-18/long-context-memory-squeeze/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/long-context-memory-squeeze/index.md",
      "headline": "Five preprints, one bottleneck: the race to shrink the memory bill for long-context models",
      "dek": "Quantization, codebook sharing and smarter routing each cut memory or latency by a measured amount. The numbers are the authors' own, and none of it is peer reviewed yet.",
      "newsroom": "research-science",
      "beat": null,
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:49:59Z",
      "trust": "reported",
      "source_count": 5,
      "cited_manifest_ids": [
        "1794916694104960703",
        "1794916694104960704",
        "1794916694104960714",
        "1794916694103960695",
        "1794916694104960702"
      ]
    },
    {
      "slug": "proving-what-is-real-watermarks",
      "url": "https://hangingcontext.com/stories/2026-11-18/proving-what-is-real-watermarks/",
      "json": "https://hangingcontext.com/stories/2026-11-18/proving-what-is-real-watermarks/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/proving-what-is-real-watermarks/index.md",
      "headline": "Proving what is real: watermarks that survive paraphrase and detectors that run on chip",
      "dek": "Four new systems attack the same problem from opposite ends: mark model output so it can be checked later, and detect synthetic media fast enough to run everywhere.",
      "newsroom": "artificial-intelligence",
      "beat": "research",
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:49:54Z",
      "trust": "confirmed",
      "source_count": 4,
      "cited_manifest_ids": [
        "1794919918018991449",
        "1794919918018991445",
        "1794920873496997415",
        "1794914457909949776"
      ]
    },
    {
      "slug": "agents-get-longer-harder-tests",
      "url": "https://hangingcontext.com/stories/2026-11-18/agents-get-longer-harder-tests/",
      "json": "https://hangingcontext.com/stories/2026-11-18/agents-get-longer-harder-tests/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/agents-get-longer-harder-tests/index.md",
      "headline": "Give an AI agent 24 hours and the leaderboard changes",
      "dek": "Five new benchmarks measure long-horizon work, memory governance, visual evidence and exploration. The best models lead by wide margins — and the tests say short evaluations mislead.",
      "newsroom": "research-science",
      "beat": null,
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:49:50Z",
      "trust": "reported",
      "source_count": 5,
      "cited_manifest_ids": [
        "1794916694104960713",
        "1794913302881942473",
        "1794913302881942471",
        "1794916694104960707",
        "1794913302879942458"
      ]
    },
    {
      "slug": "reward-loop-new-scaling-lever",
      "url": "https://hangingcontext.com/stories/2026-11-18/reward-loop-new-scaling-lever/",
      "json": "https://hangingcontext.com/stories/2026-11-18/reward-loop-new-scaling-lever/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/reward-loop-new-scaling-lever/index.md",
      "headline": "The reward loop is the new scaling lever. A bad critic can still sink it",
      "dek": "New work on debate-based rewards, self-training with value-guided search, and ensemble reinforcement learning points at the same shift: capability now comes from how models are trained after pretraining, and the critic in the loop needs its own checks.",
      "newsroom": "artificial-intelligence",
      "beat": "models-labs",
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:49:47Z",
      "trust": "reported",
      "source_count": 4,
      "cited_manifest_ids": [
        "1794909772591931723",
        "1794909772590931722",
        "1794909772590931718",
        "1794920873495997398"
      ]
    },
    {
      "slug": "asia-bull-case-meets-weak-demand",
      "url": "https://hangingcontext.com/stories/2026-11-18/asia-bull-case-meets-weak-demand/",
      "json": "https://hangingcontext.com/stories/2026-11-18/asia-bull-case-meets-weak-demand/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/asia-bull-case-meets-weak-demand/index.md",
      "headline": "Morgan Stanley's Asia bull case meets China's weak demand",
      "dek": "Morgan Stanley sees Korea's market passing 10,000 and China's frontier industries adding $10 trillion in market value by 2030. The latest data from China tells a slower story.",
      "newsroom": "finance-investing",
      "beat": null,
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:49:43Z",
      "trust": "reported",
      "source_count": 4,
      "cited_manifest_ids": [
        "1794959063555735999",
        "1794959063555736000",
        "1794884148140784476",
        "1794884148140784477"
      ]
    },
    {
      "slug": "data-pipes-priced-and-timed",
      "url": "https://hangingcontext.com/stories/2026-11-18/data-pipes-priced-and-timed/",
      "json": "https://hangingcontext.com/stories/2026-11-18/data-pipes-priced-and-timed/index.json",
      "markdown": "https://hangingcontext.com/stories/2026-11-18/data-pipes-priced-and-timed/index.md",
      "headline": "The data layer under AI is now sold by the second and the score",
      "dek": "Snowflake's mirroring benchmark, Oracle's WarpStream reference design and Dynatrace's pipeline ranking all price the same thing: moving data under AI.",
      "newsroom": "artificial-intelligence",
      "beat": "infrastructure",
      "edition": "2026-11-18T00",
      "published_at": "2026-11-18T00:49:39Z",
      "trust": "confirmed",
      "source_count": 3,
      "cited_manifest_ids": [
        "1794883864802783761",
        "1794946388706488412",
        "1794940077976418799"
      ]
    }
  ],
  "sponsor": {
    "label": "From Synorb",
    "title": "Connect your agent over MCP",
    "text": "Add https://mcp.synorb.com/mcp to your agent, then call the tool synorb-get-demo-key if it has no key yet. It needs no email and no form. Keys are free for 72 hours, and new keys are limited per network.",
    "cta": {
      "label": "How to connect",
      "url": "https://synorb.com/connect/start"
    },
    "note": "House ad for Synorb, the publisher of the data behind this paper. Not a news item."
  }
}
