{ "schema": "hangingcontext.desk/1", "type": "section", "id": "artificial-intelligence", "title": "Artificial Intelligence", "generated_at": "2026-10-15T12:46:07Z", "story_count": 44, "stories": [ { "slug": "rag-mechanics", "url": "https://hangingcontext.com/stories/2026-10-15/rag-mechanics/", "json": "https://hangingcontext.com/stories/2026-10-15/rag-mechanics/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/rag-mechanics/index.md", "headline": "More documents, worse answers: retrieval gets its mechanics audited", "dek": "Four new preprints take RAG's machinery apart: adding documents degrades retrieval through vector search dilution, frozen external memory needs a target-aligned reader, a dual-process memory cuts output tokens 73.91%, and consensus-driven evidence selection trims runtime 75.9%.", "newsroom": "artificial-intelligence", "beat": "research", "audience": "ai_developer", "edition": "2026-10-15T12", "published_at": "2026-10-15T12:46:07Z", "trust": "reported", "source_count": 4, "cited_manifest_ids": [ "1792051595354213082", "1792051595356359184", "1792051595356604559", "1792051595356646833" ] }, { "slug": "llms-meet-finance", "url": "https://hangingcontext.com/stories/2026-10-15/llms-meet-finance/", "json": "https://hangingcontext.com/stories/2026-10-15/llms-meet-finance/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/llms-meet-finance/index.md", "headline": "Finance is stress-testing LLMs and finding confident hallucinations", "dek": "Four new preprints put LLMs through finance's gauntlet: 15-23% of confident answers are wrong on FinQA, a 1,575-instance benchmark grades models by backtest rather than syntax, and proprietary models still lead open-weight ones 92.8% to 84.1% on accounting-relation extraction.", "newsroom": "artificial-intelligence", "beat": "research", "audience": "banker", "edition": "2026-10-15T12", "published_at": "2026-10-15T12:45:49Z", "trust": "confirmed", "source_count": 4, "cited_manifest_ids": [ "1792056054187313827", "1792051595356674784", "1792044246539544366", "1792044246539159128" ] }, { "slug": "lab-security-week", "url": "https://hangingcontext.com/stories/2026-10-15/lab-security-week/", "json": "https://hangingcontext.com/stories/2026-10-15/lab-security-week/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/lab-security-week/index.md", "headline": "The AI security story gets physical: toilet-paper bugs, an arrest, and malware teams with AI", "dek": "An OpenAI engineer was arrested for allegedly bugging an executive conference room — amateurishly, podcasters say — while SentinelOne and Block show what AI does for defenders.", "newsroom": "artificial-intelligence", "beat": "models-labs", "audience": "tech_exec", "edition": "2026-10-15T12", "published_at": "2026-10-15T12:45:40Z", "trust": "confirmed", "source_count": 5, "cited_manifest_ids": [ "1792014598477303412", "1792000657352320147", "1792027806007304223", "1792051672072769651", "1792051672073187732" ] }, { "slug": "kv-cache-diet", "url": "https://hangingcontext.com/stories/2026-10-15/kv-cache-diet/", "json": "https://hangingcontext.com/stories/2026-10-15/kv-cache-diet/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/kv-cache-diet/index.md", "headline": "The KV cache goes on a diet: INT2 quantization nears lossless", "dek": "Four new preprints attack LLM inference memory from four sides: crush the KV cache to INT2, protect the attention sinks, allocate bits by saliency down to 1.5 bits, or evict smarter. The numbers are striking; all are unreplicated preprint claims.", "newsroom": "artificial-intelligence", "beat": "infrastructure", "audience": "ai_developer", "edition": "2026-10-15T12", "published_at": "2026-10-15T12:45:31Z", "trust": "confirmed", "source_count": 4, "cited_manifest_ids": [ "1792034923468016998", "1792043738156128259", "1792043977262886952", "1792043977262951076" ] }, { "slug": "inference-new-map", "url": "https://hangingcontext.com/stories/2026-10-15/inference-new-map/", "json": "https://hangingcontext.com/stories/2026-10-15/inference-new-map/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/inference-new-map/index.md", "headline": "Inference is being re-priced and re-placed, one token at a time", "dek": "Intel wants your LLM workload back on CPUs with self-tuning containers; fal.ai rents B300s at $8.50 an hour; and researchers put a number on the energy cost of long context.", "newsroom": "artificial-intelligence", "beat": "infrastructure", "audience": "ai_developer", "edition": "2026-10-15T12", "published_at": "2026-10-15T12:45:22Z", "trust": "confirmed", "source_count": 5, "cited_manifest_ids": [ "1791992354059895518", "1792019924356431231", "1792043103639134716", "1791999928402715963", "1792043103639202938" ] }, { "slug": "humanoid-bottlenecks", "url": "https://hangingcontext.com/stories/2026-10-15/humanoid-bottlenecks/", "json": "https://hangingcontext.com/stories/2026-10-15/humanoid-bottlenecks/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/humanoid-bottlenecks/index.md", "headline": "The humanoid robot's real enemies: battery life and fingers", "dek": "Agility's Digit 5 charges in nine minutes for ninety minutes of work; a new benchmark finds robots that can pick up tools but not finish the job; and Japan bets on robots for a labor crisis.", "newsroom": "artificial-intelligence", "beat": "models-labs", "audience": "vc", "edition": "2026-10-15T12", "published_at": "2026-10-15T12:45:13Z", "trust": "confirmed", "source_count": 4, "cited_manifest_ids": [ "1792066244313489289", "1792043738156410205", "1792043738156787357", "1792059636319599680" ] }, { "slug": "web-agent-evals", "url": "https://hangingcontext.com/stories/2026-10-15/web-agent-evals/", "json": "https://hangingcontext.com/stories/2026-10-15/web-agent-evals/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/web-agent-evals/index.md", "headline": "Web agents now face time travel, unified shells, and distracting facts", "dek": "Four new preprints give web agents stranger tests: agents are tested against UI and workflow changes, Web$hell unifies search and browsing in one interface, SoftwareGym synthesizes 182 apps for training, and a lazy grounding attack shows factual-but-irrelevant evidence steers agents wrong.", "newsroom": "artificial-intelligence", "beat": "developers", "audience": "ai_developer", "edition": "2026-10-15T12", "published_at": "2026-10-15T12:44:14Z", "trust": "confirmed", "source_count": 4, "cited_manifest_ids": [ "1792053495086923858", "1791998379963433532", "1792053495086948162", "1792050319132020458" ] }, { "slug": "vibe-code-security", "url": "https://hangingcontext.com/stories/2026-10-15/vibe-code-security/", "json": "https://hangingcontext.com/stories/2026-10-15/vibe-code-security/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/vibe-code-security/index.md", "headline": "Your coding agent can ship features. It probably can't keep them secure.", "dek": "Two new benchmarks measure how coding agents violate task boundaries and write insecure code; Chainguard's server-side MCP servers and a live Node.js vulnerability dataset arrive as the industry's answer.", "newsroom": "artificial-intelligence", "beat": "developers", "audience": "ai_developer", "edition": "2026-10-15T12", "published_at": "2026-10-15T12:44:13Z", "trust": "confirmed", "source_count": 4, "cited_manifest_ids": [ "1791998379962955214", "1791998379962719008", "1792053500487532042", "1791988371895562036" ] }, { "slug": "training-reality-check", "url": "https://hangingcontext.com/stories/2026-10-15/training-reality-check/", "json": "https://hangingcontext.com/stories/2026-10-15/training-reality-check/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/training-reality-check/index.md", "headline": "A week of methods that don't work: self-distillation, reward hacking, and thinking leakage", "dek": "Three preprints puncture three beloved ideas — that distilling agents into themselves helps, that verifiable rewards are honest, and that RL taught models to reason.", "newsroom": "artificial-intelligence", "beat": "research", "audience": "ai_developer", "edition": "2026-10-15T12", "published_at": "2026-10-15T12:44:11Z", "trust": "confirmed", "source_count": 7, "cited_manifest_ids": [ "1792043738156529128", "1791983660771669962", "1792043738156474189", "1792066118701834392", "1792043977263661197", "1792043977263451693", "1792044246539762941" ] }, { "slug": "skill-ownership", "url": "https://hangingcontext.com/stories/2026-10-15/skill-ownership/", "json": "https://hangingcontext.com/stories/2026-10-15/skill-ownership/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/skill-ownership/index.md", "headline": "Agent skills are property now: lifecycles, watermarks, and theft", "dek": "Agent skills — reusable bundles of procedures and domain knowledge — get the full infrastructure treatment in three new preprints: retire stale skills for a 7.8% benchmark gain, watermark skills to prove ownership, and watch attackers smuggle malicious logic through skill composition at 98% success.", "newsroom": "artificial-intelligence", "beat": "developers", "audience": "ai_developer", "edition": "2026-10-15T12", "published_at": "2026-10-15T12:44:08Z", "trust": "confirmed", "source_count": 4, "cited_manifest_ids": [ "1792053495086992257", "1792050319132059742", "1792043738156226306", "1792050319131478391" ] }, { "slug": "regional-ai-playbook", "url": "https://hangingcontext.com/stories/2026-10-15/regional-ai-playbook/", "json": "https://hangingcontext.com/stories/2026-10-15/regional-ai-playbook/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/regional-ai-playbook/index.md", "headline": "Sovereign AI goes shopping: regions, cities, and a 200-billion-euro claim", "dek": "The Nordics plan 1 gigawatt of AI cloud by 2027, Britain takes a $250M safety bet, European cities build local AI factories, and Google tallies its EU footprint.", "newsroom": "artificial-intelligence", "beat": "policy", "audience": "ai_executive", "edition": "2026-10-15T12", "published_at": "2026-10-15T12:44:06Z", "trust": "confirmed", "source_count": 5, "cited_manifest_ids": [ "1792041107177675833", "1791982016634290913", "1791982016634245133", "1792003680892815534", "1792036305345212036" ] }, { "slug": "contact-center-agents", "url": "https://hangingcontext.com/stories/2026-10-15/contact-center-agents/", "json": "https://hangingcontext.com/stories/2026-10-15/contact-center-agents/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/contact-center-agents/index.md", "headline": "Telcos buy the AI-agent pitch while retail learns the hard way", "dek": "Parloa signed partnerships with AloTech and TELUS Digital to push agentic AI through contact-center channels. Meanwhile CallMiner's research says retail, the fastest adopter of automation, reports the weakest automated customer experiences of any sector.", "newsroom": "artificial-intelligence", "beat": null, "audience": "tech_exec", "edition": "2026-10-15T12", "published_at": "2026-10-15T12:44:00Z", "trust": "confirmed", "source_count": 4, "cited_manifest_ids": [ "1792053680448735291", "1791995029553984507", "1792051783451060240", "1792058127805493289" ] }, { "slug": "ai-governance-teeth", "url": "https://hangingcontext.com/stories/2026-10-15/ai-governance-teeth/", "json": "https://hangingcontext.com/stories/2026-10-15/ai-governance-teeth/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/ai-governance-teeth/index.md", "headline": "Governance gets its final exam: 12 practices, 160 comments, and 80% with an incident", "dek": "The FSB finalized its AI playbook for banks the same week IBM found eight in ten EMEA executives had an AI incident reach the board — and Anthropic hardened its election defenses.", "newsroom": "artificial-intelligence", "beat": "policy", "audience": "ai_executive", "edition": "2026-10-15T12", "published_at": "2026-10-15T12:43:56Z", "trust": "confirmed", "source_count": 5, "cited_manifest_ids": [ "1792054179960625936", "1792054179960669210", "1792031371449000209", "1792016806267567934", "1792054179960052907" ] }, { "slug": "agent-safety-benchmarks", "url": "https://hangingcontext.com/stories/2026-10-15/agent-safety-benchmarks/", "json": "https://hangingcontext.com/stories/2026-10-15/agent-safety-benchmarks/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/agent-safety-benchmarks/index.md", "headline": "Your agent can be hijacked by a fake dialog box", "dek": "Three new preprints give AI agents their own safety benchmarks: multimodal agents fall to visual hijacking at an 87.96% attack success rate, half of successful GUI runs secretly wander off track, and static cyber benchmarks are saturating.", "newsroom": "artificial-intelligence", "beat": "research", "audience": "ai_developer", "edition": "2026-10-15T12", "published_at": "2026-10-15T12:43:54Z", "trust": "reported", "source_count": 3, "cited_manifest_ids": [ "1792050319132002426", "1792050319131972967", "1792050319131817261" ] }, { "slug": "agent-pricing-chasm", "url": "https://hangingcontext.com/stories/2026-10-15/agent-pricing-chasm/", "json": "https://hangingcontext.com/stories/2026-10-15/agent-pricing-chasm/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/agent-pricing-chasm/index.md", "headline": "Everyone's deploying agents and nobody trusts them: the agentic chasm in five numbers", "dek": "G2's 2026 report says agent adoption jumped 25% but a distrust tax eats the gains; DevRev maps the pricing confusion; FirstMark bets the ledger is the real prize.", "newsroom": "artificial-intelligence", "beat": "funding-deals", "audience": "ai_founder", "edition": "2026-10-15T12", "published_at": "2026-10-15T12:43:49Z", "trust": "confirmed", "source_count": 3, "cited_manifest_ids": [ "1792003015418364308", "1791982737194113024", "1791994162864399775" ] }, { "slug": "agent-native-interfaces", "url": "https://hangingcontext.com/stories/2026-10-15/agent-native-interfaces/", "json": "https://hangingcontext.com/stories/2026-10-15/agent-native-interfaces/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/agent-native-interfaces/index.md", "headline": "Software's second interface: built for agents, not humans", "dek": "A paper synthesizes agent-native interfaces from desktop software; Web$hell unifies web access; Google puts MCP inside the enterprise cluster.", "newsroom": "artificial-intelligence", "beat": "developers", "audience": "ai_developer", "edition": "2026-10-15T00", "published_at": "2026-10-15T01:10:22Z", "trust": "reported", "source_count": 3, "cited_manifest_ids": [ "1791975921296815915", "1791998379963433532", "1792007079497882387" ] }, { "slug": "inference-time-team-allocation", "url": "https://hangingcontext.com/stories/2026-10-15/inference-time-team-allocation/", "json": "https://hangingcontext.com/stories/2026-10-15/inference-time-team-allocation/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/inference-time-team-allocation/index.md", "headline": "The new scaling law is organizational: staff your agent team like a team", "dek": "Three papers treat multi-agent compute as an allocation problem: who plans, who implements, and how the workflow learns its own latency.", "newsroom": "artificial-intelligence", "beat": "infrastructure", "audience": "ai_developer", "edition": "2026-10-15T00", "published_at": "2026-10-15T01:10:22Z", "trust": "reported", "source_count": 3, "cited_manifest_ids": [ "1792002980731885678", "1792002980731074492", "1791953638104539134" ] }, { "slug": "geo-playbook-brands-ai-answers", "url": "https://hangingcontext.com/stories/2026-10-15/geo-playbook-brands-ai-answers/", "json": "https://hangingcontext.com/stories/2026-10-15/geo-playbook-brands-ai-answers/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/geo-playbook-brands-ai-answers/index.md", "headline": "GEO grows up: the playbook for being cited by AI", "dek": "Jasper's three posts lay out the new discipline: 94% of B2B buyers use AI, 62% of citations skip the brand name, and no major AI crawler renders JavaScript.", "newsroom": "artificial-intelligence", "beat": "developers", "audience": "content_creator", "edition": "2026-10-15T00", "published_at": "2026-10-15T01:10:21Z", "trust": "reported", "source_count": 3, "cited_manifest_ids": [ "1792006191661921229", "1792006191661560686", "1792006191661549965" ] }, { "slug": "geospatial-ai-agent-stack", "url": "https://hangingcontext.com/stories/2026-10-15/geospatial-ai-agent-stack/", "json": "https://hangingcontext.com/stories/2026-10-15/geospatial-ai-agent-stack/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/geospatial-ai-agent-stack/index.md", "headline": "Agents go to orbit: the geospatial AI stack comes together", "dek": "Google's Geospatial Reasoning agent maps Ebola exposure in minutes; a paper shows planning lets small models match big ones; synthetic satellite imagery hits 90% of real-data performance.", "newsroom": "artificial-intelligence", "beat": "infrastructure", "audience": "tech_exec", "edition": "2026-10-15T00", "published_at": "2026-10-15T01:10:20Z", "trust": "confirmed", "source_count": 3, "cited_manifest_ids": [ "1792008305416862996", "1792002980731644311", "1792014233911605341" ] }, { "slug": "long-horizon-agent-worlds", "url": "https://hangingcontext.com/stories/2026-10-15/long-horizon-agent-worlds/", "json": "https://hangingcontext.com/stories/2026-10-15/long-horizon-agent-worlds/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/long-horizon-agent-worlds/index.md", "headline": "Long-horizon agents don't need bigger models. They need better worlds.", "dek": "WorkRover, Tev, WorkForge and SkillHorizon all argue agents fail for lack of good training worlds — then build them.", "newsroom": "artificial-intelligence", "beat": "research", "audience": "ai_developer", "edition": "2026-10-15T00", "published_at": "2026-10-15T01:10:19Z", "trust": "reported", "source_count": 4, "cited_manifest_ids": [ "1791975921296978240", "1791975921296829996", "1792002980731240750", "1792020952758222890" ] }, { "slug": "reward-design-post-training", "url": "https://hangingcontext.com/stories/2026-10-15/reward-design-post-training/", "json": "https://hangingcontext.com/stories/2026-10-15/reward-design-post-training/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/reward-design-post-training/index.md", "headline": "The reward is the model: three papers redesign post-training incentives", "dek": "Rubric rewards can be gamed by padding; new work redesigns the aggregation, the criteria, and the sparse-to-dense pipeline.", "newsroom": "artificial-intelligence", "beat": "research", "audience": "ai_developer", "edition": "2026-10-15T00", "published_at": "2026-10-15T01:10:18Z", "trust": "reported", "source_count": 3, "cited_manifest_ids": [ "1791953638104039048", "1791953638104282020", "1791993026512551341" ] }, { "slug": "factuality-reckoning-rag", "url": "https://hangingcontext.com/stories/2026-10-15/factuality-reckoning-rag/", "json": "https://hangingcontext.com/stories/2026-10-15/factuality-reckoning-rag/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/factuality-reckoning-rag/index.md", "headline": "The factuality reckoning: alignment rewards format, not truth", "dek": "Five alignment methods fail to beat base models on factuality; SPARK and EvoRAG take different routes to trustworthy generation.", "newsroom": "artificial-intelligence", "beat": "research", "audience": "ai_developer", "edition": "2026-10-15T00", "published_at": "2026-10-15T01:10:17Z", "trust": "reported", "source_count": 3, "cited_manifest_ids": [ "1792000908026954779", "1792000908026963703", "1792000908026716789" ] }, { "slug": "agent-memory-gets-interface", "url": "https://hangingcontext.com/stories/2026-10-15/agent-memory-gets-interface/", "json": "https://hangingcontext.com/stories/2026-10-15/agent-memory-gets-interface/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/agent-memory-gets-interface/index.md", "headline": "Memory gets an interface: see it, query it, audit it", "dek": "Sakana's My Fish visualizes chat memory; Zep v4 ships a graph Context API; researchers show procedural memory improving multi-agent scores.", "newsroom": "artificial-intelligence", "beat": "developers", "audience": "ai_developer", "edition": "2026-10-15T00", "published_at": "2026-10-15T01:10:16Z", "trust": "confirmed", "source_count": 3, "cited_manifest_ids": [ "1791996755878033271", "1791994673373062118", "1792002980731535558" ] }, { "slug": "voice-ai-full-duplex-era", "url": "https://hangingcontext.com/stories/2026-10-15/voice-ai-full-duplex-era/", "json": "https://hangingcontext.com/stories/2026-10-15/voice-ai-full-duplex-era/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/voice-ai-full-duplex-era/index.md", "headline": "Voice AI's full-duplex era: xAI goes sub-second at $0.08 a minute", "dek": "xAI ships Grok Voice 3.0 with sub-second latency; researchers shrink turn-taking to near-zero overhead; Fish Audio open-sources a 35B drama model.", "newsroom": "artificial-intelligence", "beat": "models-labs", "audience": "ai_founder", "edition": "2026-10-15T00", "published_at": "2026-10-15T01:10:15Z", "trust": "confirmed", "source_count": 3, "cited_manifest_ids": [ "1792008315037885590", "1792002980731062795", "1791975921296891460" ] }, { "slug": "video-ai-tooling-layer", "url": "https://hangingcontext.com/stories/2026-10-15/video-ai-tooling-layer/", "json": "https://hangingcontext.com/stories/2026-10-15/video-ai-tooling-layer/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/video-ai-tooling-layer/index.md", "headline": "Video AI grows up: enterprise deals, faster decoders, and physics tests", "dek": "Runway models go single-tenant via Baseten; researchers squeeze 2-4x speedups out of video VAEs; new benchmarks test whether models understand what they generate.", "newsroom": "artificial-intelligence", "beat": "models-labs", "audience": "ai_developer", "edition": "2026-10-15T00", "published_at": "2026-10-15T01:10:14Z", "trust": "reported", "source_count": 5, "cited_manifest_ids": [ "1792007767240971054", "1791998379963434596", "1791975921296323031", "1791998379963638479", "1791953638104075782" ] }, { "slug": "legal-ai-integration-race", "url": "https://hangingcontext.com/stories/2026-10-15/legal-ai-integration-race/", "json": "https://hangingcontext.com/stories/2026-10-15/legal-ai-integration-race/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/legal-ai-integration-race/index.md", "headline": "Legal AI's integration race: Legora and EvenUp agree the best model doesn't win", "dek": "Legora launches a 30+ integration ecosystem and a Sirion partnership; EvenUp bets the opposite direction — inside Word.", "newsroom": "artificial-intelligence", "beat": null, "audience": "tech_exec", "edition": "2026-10-15T00", "published_at": "2026-10-15T01:10:13Z", "trust": "reported", "source_count": 3, "cited_manifest_ids": [ "1792006786742946847", "1792006786742289775", "1792022762815894578" ] }, { "slug": "coding-benchmarks-measure-wrong-job", "url": "https://hangingcontext.com/stories/2026-10-15/coding-benchmarks-measure-wrong-job/", "json": "https://hangingcontext.com/stories/2026-10-15/coding-benchmarks-measure-wrong-job/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/coding-benchmarks-measure-wrong-job/index.md", "headline": "Only 11% of developer turns ask for code. The benchmarks test 100%.", "dek": "AI21, JetBrains session data, and a variance study all point the same way: coding-agent evals don't reflect the work.", "newsroom": "artificial-intelligence", "beat": "developers", "audience": "ai_developer", "edition": "2026-10-15T00", "published_at": "2026-10-15T01:10:12Z", "trust": "confirmed", "source_count": 4, "cited_manifest_ids": [ "1791995252927941076", "1792002986745700083", "1792005327076377136", "1792002986745470869" ] }, { "slug": "agentic-soc-shadow-automation", "url": "https://hangingcontext.com/stories/2026-10-15/agentic-soc-shadow-automation/", "json": "https://hangingcontext.com/stories/2026-10-15/agentic-soc-shadow-automation/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/agentic-soc-shadow-automation/index.md", "headline": "The SOC is going agentic — and the attackers got there first", "dek": "Shadow automation replaces shadow IT. Startups are raising to secure agents at the endpoint while papers show coordinated agents evading monitors.", "newsroom": "artificial-intelligence", "beat": "infrastructure", "audience": "tech_exec", "edition": "2026-10-15T00", "published_at": "2026-10-15T01:10:11Z", "trust": "confirmed", "source_count": 8, "cited_manifest_ids": [ "1792002330817550668", "1792014969119821065", "1792002980731460894", "1792002980731497635", "1792002980731229000", "1792002330817499567", "1792002330817466731", "1792014493570232696" ] }, { "slug": "gpu-cloud-unit-economics", "url": "https://hangingcontext.com/stories/2026-10-15/gpu-cloud-unit-economics/", "json": "https://hangingcontext.com/stories/2026-10-15/gpu-cloud-unit-economics/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-15/gpu-cloud-unit-economics/index.md", "headline": "Modal crossed $1B in run rate renting GPUs by the second, and raised $750M to rent more", "dek": "Serverless AI compute has a $15.75B poster child. fal's $8.50-per-GPU-hour B300 pricing shows what the meter looks like.", "newsroom": "artificial-intelligence", "beat": "infrastructure", "audience": "vc", "edition": "2026-10-15T00", "published_at": "2026-10-15T01:09:56Z", "trust": "confirmed", "source_count": 4, "cited_manifest_ids": [ "1791998824642026586", "1792019924356431231", "1792005890323997898", "1791991090383644175" ] }, { "slug": "world-models-robotics", "url": "https://hangingcontext.com/stories/2026-10-14/world-models-robotics/", "json": "https://hangingcontext.com/stories/2026-10-14/world-models-robotics/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-14/world-models-robotics/index.md", "headline": "Robotics' new bet: models that predict the world instead of reacting to it", "dek": "In preprints posted this week, three groups argue the same thesis from different directions: a robot that can imagine what happens next is worth more than a bigger policy that only reacts.", "newsroom": "artificial-intelligence", "beat": "infrastructure", "audience": "ai_founder", "edition": "2026-10-14T12", "published_at": "2026-10-14T14:47:57Z", "trust": "reported", "source_count": 3, "cited_manifest_ids": [ "1791975921296844581", "1791975921296829996", "1791975921296718022" ] }, { "slug": "video-models", "url": "https://hangingcontext.com/stories/2026-10-14/video-models/", "json": "https://hangingcontext.com/stories/2026-10-14/video-models/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-14/video-models/index.md", "headline": "Video AI's new trick: prove where in the video the answer came from", "dek": "Three preprints posted this week make video models cheaper to run and harder to fool: agentic evidence grounding, training-free constant-memory frame packing, and 4K super-resolution on a single consumer GPU.", "newsroom": "artificial-intelligence", "beat": "models-labs", "audience": "ai_developer", "edition": "2026-10-14T12", "published_at": "2026-10-14T14:47:44Z", "trust": "reported", "source_count": 3, "cited_manifest_ids": [ "1791975921296939250", "1791975921296874106", "1791975921296323031" ] }, { "slug": "terminal-agents", "url": "https://hangingcontext.com/stories/2026-10-14/terminal-agents/", "json": "https://hangingcontext.com/stories/2026-10-14/terminal-agents/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-14/terminal-agents/index.md", "headline": "The terminal is becoming the agent's gym: ReTerm, ClawLoop and Harness^2", "dek": "Four preprints posted this week push the same idea: agents that improve themselves inside the terminal — building their own environments, refining their own harnesses, and designing interfaces they can actually use.", "newsroom": "artificial-intelligence", "beat": "developers", "audience": "ai_developer", "edition": "2026-10-14T12", "published_at": "2026-10-14T14:47:37Z", "trust": "reported", "source_count": 4, "cited_manifest_ids": [ "1791975921296249949", "1791953638104280658", "1791953638104095030", "1791975921296815915" ] }, { "slug": "spatial-ai", "url": "https://hangingcontext.com/stories/2026-10-14/spatial-ai/", "json": "https://hangingcontext.com/stories/2026-10-14/spatial-ai/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-14/spatial-ai/index.md", "headline": "GeoReader, Urbex and EviScene: teaching AI models to read 3D space", "dek": "Three preprints push vision-language models from flat images into spatial reasoning.", "newsroom": "artificial-intelligence", "beat": "models-labs", "audience": "ai_developer", "edition": "2026-10-14T12", "published_at": "2026-10-14T14:47:24Z", "trust": "reported", "source_count": 3, "cited_manifest_ids": [ "1791973003597462477", "1791975921295266238", "1791973003597792491" ] }, { "slug": "medical-ai", "url": "https://hangingcontext.com/stories/2026-10-14/medical-ai/", "json": "https://hangingcontext.com/stories/2026-10-14/medical-ai/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-14/medical-ai/index.md", "headline": "From dictation to diagnosis: medical AI's three fronts this week", "dek": "Transcription cuts documentation time; X-Ragent and CAPTOR push vision models into radiology.", "newsroom": "artificial-intelligence", "beat": "research", "audience": "professional", "edition": "2026-10-14T12", "published_at": "2026-10-14T14:47:11Z", "trust": "confirmed", "source_count": 3, "cited_manifest_ids": [ "1791952058502820270", "1791953638104461213", "1791973003597131522" ] }, { "slug": "gui-agents", "url": "https://hangingcontext.com/stories/2026-10-14/gui-agents/", "json": "https://hangingcontext.com/stories/2026-10-14/gui-agents/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-14/gui-agents/index.md", "headline": "GUI agents learn what to remember and how to look", "dek": "In preprints posted this week: a router that picks text vs. visual memory per step, a latent world-action model that cuts inference latency 98.9%, and an evolving evidence interface that shaves 8-15% off input tokens.", "newsroom": "artificial-intelligence", "beat": "developers", "audience": "ai_developer", "edition": "2026-10-14T12", "published_at": "2026-10-14T14:46:51Z", "trust": "reported", "source_count": 3, "cited_manifest_ids": [ "1791975921296507878", "1791975921296181709", "1791953638104531873" ] }, { "slug": "enterprise-ai", "url": "https://hangingcontext.com/stories/2026-10-14/enterprise-ai/", "json": "https://hangingcontext.com/stories/2026-10-14/enterprise-ai/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-14/enterprise-ai/index.md", "headline": "Enterprise AI's quiet phase: Canva and Expedia on adoption without the hype", "dek": "Two enterprise talks this week skip the demos and discuss how AI actually gets chosen and used.", "newsroom": "artificial-intelligence", "beat": "infrastructure", "audience": "tech_exec", "edition": "2026-10-14T12", "published_at": "2026-10-14T14:46:45Z", "trust": "reported", "source_count": 3, "cited_manifest_ids": [ "1791977631661738655", "1791977631661814273", "1791920705282196464" ] }, { "slug": "deep-research-agents", "url": "https://hangingcontext.com/stories/2026-10-14/deep-research-agents/", "json": "https://hangingcontext.com/stories/2026-10-14/deep-research-agents/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-14/deep-research-agents/index.md", "headline": "Deep research agents get measured: LifeSearch, PANINI-DR and a fast-and-slow thinker", "dek": "In preprints posted this week: a 203-task benchmark where the best agent scores 63.4%, a workspace harness that beats the field by 16 points on BrowseComp-Plus, and a dual-system architecture that trades deliberation for speed.", "newsroom": "artificial-intelligence", "beat": "developers", "audience": "ai_developer", "edition": "2026-10-14T12", "published_at": "2026-10-14T14:46:38Z", "trust": "reported", "source_count": 3, "cited_manifest_ids": [ "1791975921296082254", "1791953638104294630", "1791975921296063639" ] }, { "slug": "ai-trust-backlash", "url": "https://hangingcontext.com/stories/2026-10-14/ai-trust-backlash/", "json": "https://hangingcontext.com/stories/2026-10-14/ai-trust-backlash/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-14/ai-trust-backlash/index.md", "headline": "Pony.ai fraud warnings, AI provenance, and Deezer's opt-out: the trust backlash", "dek": "Scams misusing AI brands, source-verification pitches, and music opt-outs all landed this week.", "newsroom": "artificial-intelligence", "beat": "policy", "audience": "journalist", "edition": "2026-10-14T12", "published_at": "2026-10-14T14:46:06Z", "trust": "confirmed", "source_count": 3, "cited_manifest_ids": [ "1791965826698328318", "1791904593497204282", "1791902950141057247" ] }, { "slug": "ai-infra-buildout", "url": "https://hangingcontext.com/stories/2026-10-14/ai-infra-buildout/", "json": "https://hangingcontext.com/stories/2026-10-14/ai-infra-buildout/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-14/ai-infra-buildout/index.md", "headline": "Oracle, Crusoe and Databricks all moved on AI infrastructure this week", "dek": "Cheaper flexible VMs, open-sourced Run:ai, and a best-ever Gartner debut.", "newsroom": "artificial-intelligence", "beat": "infrastructure", "audience": "tech_exec", "edition": "2026-10-14T12", "published_at": "2026-10-14T14:45:59Z", "trust": "confirmed", "source_count": 3, "cited_manifest_ids": [ "1791958297825854833", "1791905655578717275", "1791938551557500016" ] }, { "slug": "ai-funding-week", "url": "https://hangingcontext.com/stories/2026-10-14/ai-funding-week/", "json": "https://hangingcontext.com/stories/2026-10-14/ai-funding-week/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-14/ai-funding-week/index.md", "headline": "SentinelOne's $1.25B raise, a hospital OS, and games: this week's AI checks", "dek": "Security, healthcare ops, and gaming drew investor money this week.", "newsroom": "artificial-intelligence", "beat": "funding-deals", "audience": "vc", "edition": "2026-10-14T12", "published_at": "2026-10-14T14:45:53Z", "trust": "confirmed", "source_count": 3, "cited_manifest_ids": [ "1791965716725267248", "1791970283929446982", "1791960581861475986" ] }, { "slug": "agility-spac", "url": "https://hangingcontext.com/stories/2026-10-14/agility-spac/", "json": "https://hangingcontext.com/stories/2026-10-14/agility-spac/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-14/agility-spac/index.md", "headline": "A humanoid maker is going public with $300M in orders already booked", "dek": "Agility Robotics' SPAC cleared the SEC. For VCs, the question is whether committed orders convert.", "newsroom": "artificial-intelligence", "beat": "funding-deals", "audience": "vc", "edition": "2026-10-14T12", "published_at": "2026-10-14T14:45:40Z", "trust": "confirmed", "source_count": 3, "cited_manifest_ids": [ "1791934906742761271", "1791931500169422319", "1791953638104234823" ] }, { "slug": "agentic-rl-wave", "url": "https://hangingcontext.com/stories/2026-10-14/agentic-rl-wave/", "json": "https://hangingcontext.com/stories/2026-10-14/agentic-rl-wave/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-14/agentic-rl-wave/index.md", "headline": "Five ways to train agents dropped this week; two beat GRPO at the same GPU budget", "dek": "RSIPO, DeltaTTG, TPPO, Ares and SALD all target sample efficiency. In preprints posted this week, the authors report gains over GRPO and PPO baselines without proportional compute increases.", "newsroom": "artificial-intelligence", "beat": "models-labs", "audience": "ai_developer", "edition": "2026-10-14T12", "published_at": "2026-10-14T14:45:33Z", "trust": "reported", "source_count": 5, "cited_manifest_ids": [ "1791953638104635097", "1791953638104539134", "1791953638104432157", "1791953638104892525", "1791953638104894071" ] }, { "slug": "agent-ops-stack", "url": "https://hangingcontext.com/stories/2026-10-14/agent-ops-stack/", "json": "https://hangingcontext.com/stories/2026-10-14/agent-ops-stack/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-14/agent-ops-stack/index.md", "headline": "Agent ops grows up: LangSmith traces, long-running agents, live intelligence", "dek": "Three LangChain-ecosystem launches target the unglamorous work of running agents in production.", "newsroom": "artificial-intelligence", "beat": "developers", "audience": "ai_developer", "edition": "2026-10-14T12", "published_at": "2026-10-14T14:45:26Z", "trust": "reported", "source_count": 3, "cited_manifest_ids": [ "1791912247754789851", "1791912247754725895", "1791912247753700978" ] }, { "slug": "agent-evals-worlds", "url": "https://hangingcontext.com/stories/2026-10-14/agent-evals-worlds/", "json": "https://hangingcontext.com/stories/2026-10-14/agent-evals-worlds/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-14/agent-evals-worlds/index.md", "headline": "The new agent benchmarks don't test chat. Frontier models are failing them", "dek": "CineRecon, ExeWorldBench and a psychometric audit of synthetic respondents all point the same way: in preprints posted this week, the authors report that current models stumble on physical and behavioral realism.", "newsroom": "artificial-intelligence", "beat": "research", "audience": "ai_executive", "edition": "2026-10-14T12", "published_at": "2026-10-14T14:45:16Z", "trust": "reported", "source_count": 3, "cited_manifest_ids": [ "1791953638104635155", "1791953638104429191", "1791953638105360822" ] } ], "sponsor": { "label": "From Synorb", "title": "Claims with a source link", "text": "A Manifest holds a Signal of structured claims and a Brief, plus the source it came from. Your agent can check a sentence against it.", "cta": { "label": "Read the guide", "url": "https://synorb.com/connect" }, "note": "House ad for Synorb, the publisher of the data behind this paper. Not a news item." } }