{"date":"2026-11-05","title":"What happened in AI — Nov 5, 2026","generated_at":"2026-11-05T22:16:02Z","intro":["Agent builders are replacing blocking loops with async execution, explicit state machines and retry-safe tool calls.","Kimi K3.1 Pro weights shipped with day-zero Ascend support, while SemiAnalysis's GDPx shows the best model solving only 12% of long agent tasks."],"highlights":["LangChain: agents must keep working in the background yet stay responsive.","Call4Agents guarantees approved tool calls run at most once after a crash.","GDPx agent benchmark: best model scores 12%; cost per point compared for 12 models.","Moonshot releases Kimi K3.1 Pro weights and launches Kimi Hosted Agents.","OpenAI debuts GPT-6 Cyber for vulnerability discovery and fixes.","Google TPUs now serve Oracle, OpenAI, Anthropic and Meta, per SemiAnalysis."],"article_count":30,"categories":[{"name":"Agent runtimes: async, retry-safe, and state-machine control","slug":"agentic-runtimes-control","summary":"Builders are moving agents off the blocking request loop and onto explicit state, idempotent tool calls, and background execution.","articles":[{"title":"Agents Are Going Async","summary":"LangChain argues agents must stay responsive to new instructions while long jobs run in the background.","source":"langchain_blog","url":"https://www.langchain.com/blog/agents-are-going-async","published":"2026-11-05T20:00:00+00:00"},{"title":"Agent State Machines: Building Deterministic Scaffolding for Agents","summary":"Agent state machines define explicit states, events and transitions so models don't decide when work is complete.","source":"hackernews_ai","url":"https://twitter.com/josharosen/status/2117687393213932003","published":"Thu, 05 Nov 2026 01:07:15 +0000"},{"title":"Show HN: Replay three AI agent approval failures in five seconds, in Python","summary":"Call4Agents makes approved tool calls run at most once after a crash; works with LangGraph, Pydantic AI, OpenAI Agents SDK and MCP.","source":"hackernews_ai","url":"https://github.com/salahmakboul/call4agents","published":"Thu, 05 Nov 2026 18:17:19 +0000"},{"title":"Moonshot AI Launches Kimi Hosted Agents as a Managed Agent-Harness Cloud Service","summary":"Moonshot launches Kimi Hosted Agents, a managed agent-harness cloud service.","source":"search_cn_open_weight_labs","publisher_name":"Pandaily","publisher_domain":"pandaily.com","url":"https://news.google.com/rss/articles/CBMimwFBVV95cUxPX2VjT2JCMnR2VVBMeEJSMGF1N3ItbVZic21Ua1d2cGZMa1BKVHVOUVo0X2p3Zm84MnpOeGtzSEJPc0hjcmI5RXBHeEFKcHpSRDlzX2lvN1pCOS1rMkJ3U19BRGcwdjhHQmtIRDFxZ1dvUS1KaG5SN0tIM1l3LVpESnd1dHVIbXk5dTBCTzdINFVLc2J2ZndlSXlTcw?oc=5","published":"Thu, 05 Nov 2026 07:13:48 GMT"}]},{"name":"Evals and agent governance","slug":"evals-agent-governance","summary":"Agent benchmarks are exposing low ceilings and cost trade-offs, while security guidance focuses on audit-ready zero trust.","articles":[{"title":"GDPx agent benchmark: cost per point for 12 models, and the safety-filter caveat","summary":"SemiAnalysis's GDPx (206 long tasks, 11 fields) tops out at 12% for the best model; cost per point is compared across 12 models.","source":"hackernews_ai","url":"https://theainewsreport.com/2026-11-05-semianalysis-gdpx-agent-benchmark-cost-per-point-explained.html","published":"Thu, 05 Nov 2026 19:13:23 +0000"},{"title":"Presentation: Zero Trust Agent Systems that Pass Audits and Still Ship","summary":"InfoQ talk on zero-trust agent architectures that pass audits without blocking shipping.","source":"infoq_ai_ml","url":"https://www.infoq.com/presentations/zero-trust-ai-agents-production-security/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=AI%2C+ML+%26+Data+Engineering","published":"Thu, 05 Nov 2026 11:00:00 GMT"}]},{"name":"Inference infrastructure and compute","slug":"inference-infrastructure-compute","summary":"Inference stacks are being optimized at the control-plane, compiler and memory layers, with Google TPUs gaining ground.","articles":[{"title":"The Iron(wood) Throne: Google's TPU Stakes Its Claim on Inference","summary":"SemiAnalysis says Google TPUs now have external customers including Oracle, OpenAI, Anthropic and Meta, and a growing software ecosystem.","source":"semianalysis","url":"https://newsletter.semianalysis.com/p/tpu-strikes-the-king","published":"Thu, 05 Nov 2026 19:03:45 GMT"},{"title":"Distributed Inference Benchmarks: [K]Inference vs. Plain Kubernetes","summary":"Buoyant benchmarks Kinference, a Kubernetes/vLLM control plane for heterogeneous GPUs, against plain Kubernetes.","source":"hackernews_ai","url":"https://www.buoyant.io/blog/distributed-inference-benchmarks-kinference-vs-plain-kubernetes","published":"Thu, 05 Nov 2026 19:07:41 +0000"},{"title":"Together AI Compiler for Inference","summary":"Together AI's compiler uses agents to continually optimize inference across new models, hardware and traffic shapes.","source":"hackernews_ai","url":"https://www.together.ai/blog/together-compiler-continual-compilation-for-ai-inference","published":"Thu, 05 Nov 2026 15:07:35 +0000"},{"title":"More Performance From Every Byte: How Full-Stack Codesign Solves AI’s Memory Challenge","summary":"NVIDIA details full-stack codesign with memory partners to ease GPU memory pressure from long contexts and agents.","source":"nvidia_blog","url":"https://blogs.nvidia.com/blog/memory-full-stack-codesign/","published":"Thu, 05 Nov 2026 16:00:00 +0000"}]},{"name":"Models and open weights","slug":"models-open-weights","summary":"Kimi K3.1 Pro weights landed with same-day Ascend support, and GPT-6 Cyber targets vulnerability finding and fixing.","articles":[{"title":"Moonshot AI Publishes Kimi K3.1 Pro Weights on Hugging Face","summary":"Moonshot AI publishes Kimi K3.1 Pro weights on Hugging Face.","source":"search_cn_open_weight_labs","publisher_name":"www.tokenpost.com","publisher_domain":"tokenpost.com","url":"https://news.google.com/rss/articles/CBMiW0FVX3lxTE5FV2ROOGlfZC1mOU1EUTFyVjdIMlBnSElscXdfNDNiU2JkYlMxUHVhWnd0aE5NUzlVcjQtc3plaFdWSmpVcWpkc1pNSkF3bWpsa2JZSUtYUkVVTDQ?oc=5","published":"Thu, 05 Nov 2026 11:04:21 GMT"},{"title":"Huawei Ascend Adds Day-Zero Support for Kimi K3.1 Pro Across Atlas A3 and Ascend 950 SuperPoDs","summary":"Huawei Ascend adds day-zero support for Kimi K3.1 Pro on Atlas A3 and Ascend 950 SuperPoDs.","source":"search_cn_open_weight_labs","publisher_name":"Pandaily","publisher_domain":"pandaily.com","url":"https://news.google.com/rss/articles/CBMipAFBVV95cUxPc1M4OXNUei1jbTVEbnNVLU4zVWtwZEE3ek9kTjdCYmhmd3RoQ09DRU0wN18ycjN2LXdreDcyYkFLeU9aTm5aNDVTRmZieFU4LXNZSlRVbGlFeHBEQzlBLTJKXzFzWG9lMThZZlBhemdhbjNGdHhjdUFyWS1TaXRmNk0xX2U5dzJGbnhWalBwSXpUR1hRZ3hvMXBiOXlRbVJwZmRuaA?oc=5","published":"Thu, 05 Nov 2026 02:27:42 GMT"},{"title":"GPT‑6 Cyber: Advancing the frontier of aligned cybersecurity agents","summary":"OpenAI introduces GPT-6 Cyber, a model for finding exploitable vulnerabilities and developing fixes within authorized scope.","source":"openai_blog","url":"https://openai.com/index/introducing-gpt-6-cyber","published":"Thu, 05 Nov 2026 09:00:00 GMT"}]}],"video":{"youtube_id":"6GSOHhxw4lY","title":"LLM Digest Daily Explainer: Nov 5, 2026","duration_s":119.1}}