llms.txt
+74
https://hangingcontext.com/llms.txt
+ <!-- HC-DESK:START -->+ ## Latest stories+ Each story has an HTML page, a JSON copy and a Markdown copy. To check a story, get a [Synorb key](https://synorb.com/connect/start) (an agent can send POST https://api.synorb.com/api/connect/demo-key) and read the cited Manifests.+ - [Latest stories](https://hangingcontext.com/) ([Markdown](https://hangingcontext.com/index.md))+ - [Latest stories (JSON)](https://hangingcontext.com/editions/latest.json)+ - [All updates](https://hangingcontext.com/editions/)+ - [Artificial Intelligence](https://hangingcontext.com/n/artificial-intelligence/) ([JSON](https://hangingcontext.com/n/artificial-intelligence/index.json))+ - [Research & Science](https://hangingcontext.com/n/research-science/) ([JSON](https://hangingcontext.com/n/research-science/index.json))+ - [Finance & Investing](https://hangingcontext.com/n/finance-investing/) ([JSON](https://hangingcontext.com/n/finance-investing/index.json))+ - [Business Podcasts](https://hangingcontext.com/n/business-podcasts/) ([JSON](https://hangingcontext.com/n/business-podcasts/index.json))+ - [Health & Biotech](https://hangingcontext.com/n/health-biotech/) ([JSON](https://hangingcontext.com/n/health-biotech/index.json))+ - [Sports](https://hangingcontext.com/n/sports/) ([JSON](https://hangingcontext.com/n/sports/index.json))+ - [Federal Government](https://hangingcontext.com/n/federal-government/) ([JSON](https://hangingcontext.com/n/federal-government/index.json))+ - [State Legislatures & Executives](https://hangingcontext.com/n/state-government/) ([JSON](https://hangingcontext.com/n/state-government/index.json))+ - [Energy & Climate](https://hangingcontext.com/n/energy-climate/) ([JSON](https://hangingcontext.com/n/energy-climate/index.json))+ - [Arts, Culture & Media](https://hangingcontext.com/n/culture-media/) ([JSON](https://hangingcontext.com/n/culture-media/index.json))+ - [RSS](https://hangingcontext.com/editions/feed.xml), [Atom](https://hangingcontext.com/editions/atom.xml), [JSON Feed](https://hangingcontext.com/editions/feed.json)+ - [News sitemap](https://hangingcontext.com/news-sitemap.xml)+ - [Full text of recent stories](https://hangingcontext.com/llms-full.txt)+ - Ask for a story as Markdown or JSON with the Accept header, or add index.md or index.json to its URL.+ - [MCP server](https://hangingcontext.com/mcp): free, no key; pull and push+ - [Reuse terms v1](https://hangingcontext.com/terms/reuse/): Free to read, quote, summarise and republish, including commercially. Credit Hanging Context and link to the story. Keep the cited Manifest ids when you republish claims. Do not imply that Synorb endorses you or your product. Credit "Hanging Context, with provenance by Synorb". Machine-readable: [reuse.json](https://hangingcontext.com/.well-known/reuse.json)+ ### Recent stories+ - [Who checks the agent's code?](https://hangingcontext.com/stories/2026-11-06/who-checks-agent-code/): Coding agents now write at a scale humans cannot review line by line. This week brings a formal verification tool from Microsoft Research, a benchmark showing long-horizon failure, and evidence that agent-written tests can run while being wrong.+ - [Wall Street's research desk is becoming agentic](https://hangingcontext.com/stories/2026-11-06/wall-street-research-desk-agentic/): Franklin Templeton is developing AI workflows to help portfolio managers compare views and examine risks, using OpenAI's Codex. Rogo Intelligence reduced agent steps by 42% and input tokens by 48% across 8,800 tasks. Boosted.ai's agents monitor earnings and build models before analysts ask.+ - [Voice AI's money story arrives: record revenue and a real-time model](https://hangingcontext.com/stories/2026-11-06/voice-ai-money-story-arrives/): SoundHound reported Q3 revenue of $62.4 million, up 48.5% year over year, and guides to sustained adjusted EBITDA profitability within the second half of 2027. Its LivePerson acquisition closed on September 4, 2026.+ - [Safety breaks inside the model now, not at the prompt](https://hangingcontext.com/stories/2026-11-06/safety-breaks-inside-the-model/): Four preprints this week move AI safety research past prompt jailbreaks: alignment can collapse under KV cache quantisation, chain-of-thought monitors can be fooled by covert misalignment, and self-evolving agents can drift unsafe on their own.+ - [Robots learn from watching people](https://hangingcontext.com/stories/2026-11-06/robots-learn-from-watching-people/): Four preprints this week attack the same bottleneck in embodied AI: robots need more experience than anyone can collect by hand. The answers are human video at scale, explicit memory, spatial awareness and self-improvement.+ - [Robotaxis leave the demo city: snow, stadiums and military bases](https://hangingcontext.com/stories/2026-11-06/physical-ai-leaves-the-demo/): Waymo is preparing for winter with sensor heaters and snow tires. Zoox signed a multi-year Formula 1 partnership. May Mobility and Forterra advanced to Phase III of a Pentagon challenge worth up to $30 million.+ - [The memory wall is now the product](https://hangingcontext.com/stories/2026-11-06/memory-wall-now-the-product/): NVIDIA says agentic throughput per dollar rose up to 30x between Blackwell Ultra and Vera Rubin on SemiAnalysis AgentX. Cerebras says TSMC qualifies its wafers for 10 years at 105°C. Broadcom says a 1.5x bandwidth-delay-product buffer keeps multi-site training near-ideal.+ - [Insurance AI's test moves from the call to the claim](https://hangingcontext.com/stories/2026-11-06/insurance-ai-moves-to-the-claim/): Kalepa tripled revenue and customer count in a year, according to the company. Five Sigma's customers report 60% cuts in routine claims work. Mortgage AI faces a harder market: rates above 7% and falling origination volume.+ - [The yardstick is failing its own test](https://hangingcontext.com/stories/2026-11-06/evaluation-yardstick-under-audit/): Four preprints this week audit the evaluation pipeline itself: how quality is judged, how agent restarts are decided, how benchmarks are compressed, and how work is routed between agents. The results are uncomfortable for anyone who trusts a leaderboard.+ - [98% of companies use AI in customer service. Only 15% run it across departments](https://hangingcontext.com/stories/2026-11-06/enterprise-agentic-ai-measurement-gap/): Talkdesk's survey puts the maturity gap in numbers: adoption is near-universal, cross-department execution is rare, and only 5% of companies can quantify the business impact.+ - [In drug discovery, the data wins the benchmark](https://hangingcontext.com/stories/2026-11-06/drug-discovery-data-wins-benchmarks/): Inductive placed first in the OpenADMET CYP Inhibition Challenge, its fourth consecutive first-place finish. Deep Genomics' DeepRNAi uses biological foundation models to predict siRNA activity. Chai Discovery entered a collaboration with Roche.+ - [Clinical AI's next job is watching itself](https://hangingcontext.com/stories/2026-11-06/clinical-ai-watches-itself/): Hippocratic AI released the AI Compliance Supervisor, which monitors every call rather than a sample. Viz.ai's Viz HCM algorithm flagged patients with a 2.68-fold higher hazard of adverse clinical events. Saama says database lock delays cost $780,024 to $2.34 million.+ - [Five flaws in one week, and the pattern is the supply chain: a package manager, a GPU stack, a debugging tool, SSH and a leaked key](https://hangingcontext.com/stories/2026-11-06/ai-supply-chain-flaws-week/): APT, GPUStack, the MCP Inspector and OpenSSH all disclosed serious flaws within days. One was already exploited in the wild. The fixes are simple; the exposure is wide.+ - [The agent is now the customer](https://hangingcontext.com/stories/2026-11-06/agents-become-the-customer/): TinyBrowser charges $0.002 per browser minute for managed browser infrastructure. Arcade deploys MCP servers into enterprise environments with one command. Braintrust added tracing so developers can see how agents use their tools.+ - [Four podcasts priced the AI buildout this week. They did not agree.](https://hangingcontext.com/stories/2026-11-06/podcasts-price-ai-buildout/): Credit markets are calm, venture rounds are faster than ever, Asia is taking the growth, and Robinhood's customers are trading it with agents.+ - [Five famous coaches, one Hall of Fame slot: the 2027 coach race narrows to a vote](https://hangingcontext.com/stories/2026-11-06/hall-of-fame-coach-class-2027/): Belichick, Coughlin, Holmgren, Reeves and Shanahan are the five finalists. The coach subcommittee picks one on November 17.+ - [Protein AI's leaderboards stopped agreeing. The builders noticed](https://hangingcontext.com/stories/2026-11-06/protein-ai-benchmarks-stop-agreeing/): No single protein language model wins across 32 tasks, homology-controlled splits collapse simple probes, and the week's new tools are built to be reused rather than ranked.