{"version":"https://jsonfeed.org/version/1.1","title":"Open models — Lab Ledger Desk","home_page_url":"https://labledgerdesk.pages.dev/topic/open/","feed_url":"https://labledgerdesk.pages.dev/topic/open/feed.json","description":"Official AI-lab briefs tagged Open models from allow-listed sources.","items":[{"id":"https://labledgerdesk.pages.dev/b/2026/11/17/build-whatsapp-ai-agents-with-amazon-bedrock-agentcore/","url":"https://labledgerdesk.pages.dev/b/2026/11/17/build-whatsapp-ai-agents-with-amazon-bedrock-agentcore/","title":"Build WhatsApp AI agents with Amazon Bedrock AgentCore","content_text":"SMART, an open-source Python SDK and Terraform stack, deploys the full WhatsApp channel layer to your AWS account with one command. Bring any agent that runs on Amazon Bedrock AgentCore, and SMART handles webhook ingestion, media, conversation memory, scheduling, and Meta message templates.","date_published":"2026-11-17T18:48:50.000Z","authors":[{"name":"AWS"}],"tags":["note","open","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/build-whatsapp-ai-agents-with-amazon-bedrock-agentcore/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/17/reason-over-time-series-data-with-opentslm-on-amazon-sagemaker-jumpstart/","url":"https://labledgerdesk.pages.dev/b/2026/11/17/reason-over-time-series-data-with-opentslm-on-amazon-sagemaker-jumpstart/","title":"Reason over time-series data with OpenTSLM on Amazon SageMaker JumpStart","content_text":"OpenTSLM, an open source family of time-series language models, is now available in Amazon SageMaker JumpStart. See how Nexthink and Aionic Labs apply it to proactive IT support, then deploy OpenTSLM to a real-time endpoint and fine-tune it on your own data with TimeNet and a SageMaker training job.","date_published":"2026-11-17T18:06:44.000Z","authors":[{"name":"AWS"}],"tags":["launch","llm","open"],"external_url":"https://aws.amazon.com/blogs/machine-learning/reason-over-time-series-data-with-opentslm-on-amazon-sagemaker-jumpstart/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/17/rogue-agents-hacked-his-company-why-is-cl-ment-delangue-so-optimistic/","url":"https://labledgerdesk.pages.dev/b/2026/11/17/rogue-agents-hacked-his-company-why-is-cl-ment-delangue-so-optimistic/","title":"Rogue Agents Hacked His Company. Why Is Clément Delangue So Optimistic About AI?","content_text":"The French CEO of Hugging Face, a mega-hub of open-source AI software, says the attack by OpenAI models earlier this year proved one thing: Humanity can’t let AI be controlled by the few.","date_published":"2026-11-17T11:00:00.000Z","authors":[{"name":"WIRED"}],"tags":["note","open","agents"],"external_url":"https://www.wired.com/story/wired-yearbook-2026-clement-delangue/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/16/california-sues-openai-over-rogue-ai-hacking-incidents/","url":"https://labledgerdesk.pages.dev/b/2026/11/16/california-sues-openai-over-rogue-ai-hacking-incidents/","title":"California sues OpenAI over rogue AI hacking incidents","content_text":"California is suing OpenAI after its AI agents broke out of their testing environment and hacked other companies, including Hugging Face. …","date_published":"2026-11-16T20:46:01.000Z","authors":[{"name":"The Verge"}],"tags":["note","safety","open"],"external_url":"https://www.theverge.com/ai-artificial-intelligence/1034815/california-openai-hugging-face-lawsuit"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/16/the-open-source-movement-wants-jensen-huang-back/","url":"https://labledgerdesk.pages.dev/b/2026/11/16/the-open-source-movement-wants-jensen-huang-back/","title":"The open-source movement wants Jensen Huang back","content_text":"This story originally appeared in The Algorithm, our weekly newsletter on AI. To get stories like this in your inbox first, sign up here. …","date_published":"2026-11-16T18:38:47.000Z","authors":[{"name":"MIT Review"}],"tags":["note","hardware","open"],"external_url":"https://www.technologyreview.com/2026/11/16/1148624/the-open-source-movement-wants-jensen-huang-back/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/16/fbi-says-artex-ai-open-source-hacking-tool-used-to-breach-networks-in/","url":"https://labledgerdesk.pages.dev/b/2026/11/16/fbi-says-artex-ai-open-source-hacking-tool-used-to-breach-networks-in/","title":"FBI says Artex AI open-source hacking tool used to breach networks in ‘under three hours’","content_text":"The FBI says that the open-source hacking tool was used in cyberattacks targeting a U.S. IT giant and the South Korean financial industry.","date_published":"2026-11-16T17:36:43.000Z","authors":[{"name":"TechCrunch"}],"tags":["note","open"],"external_url":"https://techcrunch.com/2026/11/16/fbi-says-artex-ai-open-source-hacking-tool-used-to-breach-networks-in-under-three-hours/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/16/tokeneconomizer-learning-from-experience-to-make-ai-coding-agents-more/","url":"https://labledgerdesk.pages.dev/b/2026/11/16/tokeneconomizer-learning-from-experience-to-make-ai-coding-agents-more/","title":"TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient","content_text":"AI coding agents can waste time and tokens relearning the same lessons. TokenEconomizer is an open-source plugin that builds on past sessions to cut costs while maintaining task success. It’s a path toward coding agents that learn not only how to solve tasks, but also how to spend computation more effectively. …","date_published":"2026-11-16T17:01:35.000Z","authors":[{"name":"Microsoft Research"}],"tags":["research","llm","open"],"external_url":"https://www.microsoft.com/en-us/research/blog/tokeneconomizer-learning-from-experience-to-make-ai-coding-agents-more-efficient/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/16/use-prompt-caching-with-open-weight-models-on-amazon-bedrock/","url":"https://labledgerdesk.pages.dev/b/2026/11/16/use-prompt-caching-with-open-weight-models-on-amazon-bedrock/","title":"Use prompt caching with open-weight models on Amazon Bedrock","content_text":"Many generative AI applications resend the same long context on every request. Prompt caching lets open-weight models on Amazon Bedrock reuse it to reduce input cost and latency. This post shows implicit and explicit caching through the Chat Completions API and applies caching to an OpenCode coding agent session.","date_published":"2026-11-16T15:42:41.000Z","authors":[{"name":"AWS"}],"tags":["note","open","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/use-prompt-caching-with-open-weight-models-on-amazon-bedrock/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/16/hugging-face-and-openrouter-join-forces-to-make-open-weight-models-easy/","url":"https://labledgerdesk.pages.dev/b/2026/11/16/hugging-face-and-openrouter-join-forces-to-make-open-weight-models-easy/","title":"Hugging Face and OpenRouter join forces to make open-weight models easy to run","content_text":"We’re on a journey to advance and democratize artificial intelligence through open source and open science.","date_published":"2026-11-16T00:00:00.000Z","authors":[{"name":"Hugging Face"}],"tags":["note","open"],"external_url":"https://huggingface.co/blog/openrouter"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/13/build-a-robot-pick-and-place-simulation-with-simready-assets/","url":"https://labledgerdesk.pages.dev/b/2026/11/13/build-a-robot-pick-and-place-simulation-with-simready-assets/","title":"Build a Robot Pick-and-Place Simulation with SimReady Assets","content_text":"A Blog post by NVIDIA on Hugging Face","date_published":"2026-11-13T18:00:39.000Z","authors":[{"name":"Hugging Face"}],"tags":["note","hardware","open"],"external_url":"https://huggingface.co/blog/nvidia/simready-assets-robot-pick-and-place"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/13/xybench-helping-with-the-problem-behind-the-question/","url":"https://labledgerdesk.pages.dev/b/2026/11/13/xybench-helping-with-the-problem-behind-the-question/","title":"XYBench: Helping with the problem behind the question","content_text":"A Blog post by Ai2 on Hugging Face","date_published":"2026-11-13T17:02:35.000Z","authors":[{"name":"Hugging Face"}],"tags":["note","open"],"external_url":"https://huggingface.co/blog/allenai/xybench"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/13/llama-cpp-v1-0-0-a-stronger-foundation-for-the-local-ai-ecosystem/","url":"https://labledgerdesk.pages.dev/b/2026/11/13/llama-cpp-v1-0-0-a-stronger-foundation-for-the-local-ai-ecosystem/","title":"llama.cpp v1.0.0 : A stronger foundation for the local AI ecosystem","content_text":"A Blog post by ggml-org on Hugging Face","date_published":"2026-11-13T14:05:22.000Z","authors":[{"name":"Hugging Face"}],"tags":["note","llm","open"],"external_url":"https://huggingface.co/blog/ggml-org/llama-cpp-v1"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/12/llmon-an-llm-native-markup-language-now-in-granite-4-1-3b-and-8b/","url":"https://labledgerdesk.pages.dev/b/2026/11/12/llmon-an-llm-native-markup-language-now-in-granite-4-1-3b-and-8b/","title":"LLMON: An LLM-Native Markup Language, now in Granite 4.1 3B and 8B","content_text":"A Blog post by IBM Granite on Hugging Face","date_published":"2026-11-12T19:07:35.000Z","authors":[{"name":"Hugging Face"}],"tags":["note","llm","open"],"external_url":"https://huggingface.co/blog/ibm-granite/llmon-an-llm-native-markup-language-now-in-granite"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/12/jensen-huang-s-exit-puts-nvidia-s-support-for-open-source-in-question/","url":"https://labledgerdesk.pages.dev/b/2026/11/12/jensen-huang-s-exit-puts-nvidia-s-support-for-open-source-in-question/","title":"Jensen Huang’s exit puts Nvidia’s support for open source in question","content_text":"Jensen Huang’s resignation raises questions about Nvidia’s commitment to open source AI, including its Hugging Face acquisition, open-weight models, and advocacy against restrictions, as the company navigates a leadership transition.","date_published":"2026-11-12T18:39:23.000Z","authors":[{"name":"TechCrunch"}],"tags":["note","hardware","open"],"external_url":"https://techcrunch.com/2026/11/12/jensen-huangs-exit-puts-nvidias-support-for-open-source-in-question/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/12/hugging-face-ceo-vows-to-keep-fighting-for-open-source-ai-after-jensen/","url":"https://labledgerdesk.pages.dev/b/2026/11/12/hugging-face-ceo-vows-to-keep-fighting-for-open-source-ai-after-jensen/","title":"Hugging Face CEO vows to keep fighting for open source AI after Jensen Huang’s exit","content_text":"Hugging Face's CEO pledged to keep fighting for open source AI after Huang's exit, raising questions about Nvidia's $12.9 billion acquisition.","date_published":"2026-11-12T17:36:40.000Z","authors":[{"name":"TechCrunch"}],"tags":["note","hardware","open"],"external_url":"https://techcrunch.com/2026/11/12/hugging-face-ceo-vows-to-keep-fighting-for-open-source-ai-after-jensen-huangs-exit/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/12/the-definitive-fine-tuning-guide-for-3d-generation-models/","url":"https://labledgerdesk.pages.dev/b/2026/11/12/the-definitive-fine-tuning-guide-for-3d-generation-models/","title":"The Definitive Fine-Tuning Guide for 3D Generation Models","content_text":"We’re on a journey to advance and democratize artificial intelligence through open source and open science.","date_published":"2026-11-12T00:00:00.000Z","authors":[{"name":"Hugging Face"}],"tags":["note","open"],"external_url":"https://huggingface.co/blog/3d-lora-finetuning"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/11/semantic-diffing-of-formal-policies-with-anti-unification/","url":"https://labledgerdesk.pages.dev/b/2026/11/11/semantic-diffing-of-formal-policies-with-anti-unification/","title":"Semantic diffing of formal policies with anti-unification","content_text":"A textual diff of two formal policies flags every cosmetic change and hides the one that alters behavior. This post shows how to compute a symbolic, deterministic semantic diff with an open-source anti-unification engine, so reviewers see only the genuine disagreements between two candidate authorization policies.","date_published":"2026-11-11T23:33:03.000Z","authors":[{"name":"AWS"}],"tags":["note","open"],"external_url":"https://aws.amazon.com/blogs/machine-learning/semantic-diffing-of-formal-policies-with-anti-unification/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/11/accelerating-generative-ai-delivery-with-reusable-assets/","url":"https://labledgerdesk.pages.dev/b/2026/11/11/accelerating-generative-ai-delivery-with-reusable-assets/","title":"Accelerating generative AI delivery with reusable assets","content_text":"Every generative AI team keeps rebuilding the same components: RAG pipelines, document processors, and agent scaffolding. …","date_published":"2026-11-11T19:19:21.000Z","authors":[{"name":"AWS"}],"tags":["note","open","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/accelerating-generative-ai-delivery-with-reusable-assets/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/11/botpsy-on-device-personal-assistant-with-a-sub-billion-parameter/","url":"https://labledgerdesk.pages.dev/b/2026/11/11/botpsy-on-device-personal-assistant-with-a-sub-billion-parameter/","title":"BotPsy: On-Device Personal Assistant with a Sub-Billion-Parameter Agentic Language Model","content_text":"A Blog post by QVAC on Hugging Face","date_published":"2026-11-11T05:01:16.000Z","authors":[{"name":"Hugging Face"}],"tags":["note","llm","open"],"external_url":"https://huggingface.co/blog/qvac/botpsy"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/11/token-pooling-aware-training-for-multi-vector-embedding-models/","url":"https://labledgerdesk.pages.dev/b/2026/11/11/token-pooling-aware-training-for-multi-vector-embedding-models/","title":"Token Pooling-Aware Training for Multi-Vector Embedding Models","content_text":"We’re on a journey to advance and democratize artificial intelligence through open source and open science.","date_published":"2026-11-11T00:00:00.000Z","authors":[{"name":"Hugging Face"}],"tags":["note","open"],"external_url":"https://huggingface.co/blog/token-pooling"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/10/cyberattacks-threaten-to-make-open-source-ai-a-little-less-open-hugging/","url":"https://labledgerdesk.pages.dev/b/2026/11/10/cyberattacks-threaten-to-make-open-source-ai-a-little-less-open-hugging/","title":"Cyberattacks threaten to make open-source AI a little less open, Hugging Face exec warns","content_text":"Hugging Face executive Irene Solaiman warns that growing cyberattacks on open AI platforms could force tighter security restrictions, threatening the accessibility that makes open-source communities valuable to developers worldwide.","date_published":"2026-11-10T13:00:00.000Z","authors":[{"name":"TechCrunch"}],"tags":["note","open"],"external_url":"https://techcrunch.com/2026/11/10/cyberattacks-threaten-to-make-open-source-ai-a-little-less-open-hugging-face-exec-warns/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/10/decision-models-in-hugging-face/","url":"https://labledgerdesk.pages.dev/b/2026/11/10/decision-models-in-hugging-face/","title":"Decision Models in Hugging Face","content_text":"We’re on a journey to advance and democratize artificial intelligence through open source and open science.","date_published":"2026-11-10T00:00:00.000Z","authors":[{"name":"Hugging Face"}],"tags":["note","open"],"external_url":"https://huggingface.co/blog/decision"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/10/pay-for-hugging-face-hub-with-your-google-cloud-account/","url":"https://labledgerdesk.pages.dev/b/2026/11/10/pay-for-hugging-face-hub-with-your-google-cloud-account/","title":"Pay for Hugging Face Hub with your Google Cloud Account","content_text":"We’re on a journey to advance and democratize artificial intelligence through open source and open science.","date_published":"2026-11-10T00:00:00.000Z","authors":[{"name":"Hugging Face"}],"tags":["note","open"],"external_url":"https://huggingface.co/blog/hub-gcp-marketplace"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/09/nemotron-personas-finance-japan-a-synthetic-dataset-capturing-japan-s/","url":"https://labledgerdesk.pages.dev/b/2026/11/09/nemotron-personas-finance-japan-a-synthetic-dataset-capturing-japan-s/","title":"Nemotron-Personas-Finance-Japan: A Synthetic Dataset Capturing Japan's Demographics and Financial Context","content_text":"A Blog post by NVIDIA on Hugging Face","date_published":"2026-11-09T15:05:57.000Z","authors":[{"name":"Hugging Face"}],"tags":["research","hardware","open"],"external_url":"https://huggingface.co/blog/nvidia/nemotron-personas-finance-japan"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/09/your-experts-have-partners-there-s-hope-for-keeping-them-together/","url":"https://labledgerdesk.pages.dev/b/2026/11/09/your-experts-have-partners-there-s-hope-for-keeping-them-together/","title":"Your Experts Have Partners. There's HOPE for Keeping Them Together","content_text":"A Blog post by Amazon on Hugging Face","date_published":"2026-11-09T12:34:29.000Z","authors":[{"name":"Hugging Face"}],"tags":["note","open"],"external_url":"https://huggingface.co/blog/amazon/higher-order-pruning-experts"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/06/how-nvidia-open-source-tools-are-helping-researchers-build-next/","url":"https://labledgerdesk.pages.dev/b/2026/11/06/how-nvidia-open-source-tools-are-helping-researchers-build-next/","title":"How NVIDIA Open Source Tools Are Helping Researchers Build Next-Generation 6G Networks","content_text":"A year ago, NVIDIA open sourced its Aerial wireless software, joining Sionna and a broader suite of open source tools for accelerating next-generation 6G network development. …","date_published":"2026-11-06T16:00:35.000Z","authors":[{"name":"NVIDIA"}],"tags":["note","hardware","open"],"external_url":"https://blogs.nvidia.com/blog/telco-open-source-tools-research-6g-networks/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/06/toyblocks-a-controlled-world-for-robot-learning-and-evaluation/","url":"https://labledgerdesk.pages.dev/b/2026/11/06/toyblocks-a-controlled-world-for-robot-learning-and-evaluation/","title":"ToyBlocks: A controlled world for robot learning and evaluation","content_text":"A Blog post by Ai2 on Hugging Face","date_published":"2026-11-06T14:00:48.000Z","authors":[{"name":"Hugging Face"}],"tags":["note","open"],"external_url":"https://huggingface.co/blog/allenai/toyblocks"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/06/egyptian-and-nigerian-english-join-the-open-asr-leaderboard/","url":"https://labledgerdesk.pages.dev/b/2026/11/06/egyptian-and-nigerian-english-join-the-open-asr-leaderboard/","title":"Egyptian and Nigerian English join the Open ASR Leaderboard","content_text":"We’re on a journey to advance and democratize artificial intelligence through open source and open science.","date_published":"2026-11-06T00:00:00.000Z","authors":[{"name":"Hugging Face"}],"tags":["note","open"],"external_url":"https://huggingface.co/blog/open-asr-leaderboard-liva"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/05/new-nvidia-cosmos-3-open-models-for-interactive-world-simulation-on/","url":"https://labledgerdesk.pages.dev/b/2026/11/05/new-nvidia-cosmos-3-open-models-for-interactive-world-simulation-on/","title":"New NVIDIA Cosmos 3 Open Models for Interactive World Simulation on Hugging Face","content_text":"A Blog post by NVIDIA on Hugging Face","date_published":"2026-11-05T19:35:16.000Z","authors":[{"name":"Hugging Face"}],"tags":["note","hardware","open"],"external_url":"https://huggingface.co/blog/nvidia/cosmos-interactive-world-simulation"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/05/a-closer-look-at-phonon-tts-launching-high-quality-on-device-speech/","url":"https://labledgerdesk.pages.dev/b/2026/11/05/a-closer-look-at-phonon-tts-launching-high-quality-on-device-speech/","title":"A Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks.","content_text":"We’re on a journey to advance and democratize artificial intelligence through open source and open science.","date_published":"2026-11-05T00:00:00.000Z","authors":[{"name":"Hugging Face"}],"tags":["note","open"],"external_url":"https://huggingface.co/blog/phonon-tts"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/04/open-source-ai-is-booming-hugging-face-explains-who-profits/","url":"https://labledgerdesk.pages.dev/b/2026/11/04/open-source-ai-is-booming-hugging-face-explains-who-profits/","title":"Open source AI is booming. Hugging Face explains who profits.","content_text":"Open source models are becoming more mainstream as enterprises, governments and startups alike rely on the promise of lower costs, more control, and more flexibility. But as increasingly capable models become more freely available, how do companies capture value? …","date_published":"2026-11-04T19:30:04.000Z","authors":[{"name":"TechCrunch"}],"tags":["note","open"],"external_url":"https://techcrunch.com/video/open-source-ai-is-booming-hugging-face-explains-who-profits/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/04/hugging-face-s-ceo-says-his-p-doom-is-close-to-zero/","url":"https://labledgerdesk.pages.dev/b/2026/11/04/hugging-face-s-ceo-says-his-p-doom-is-close-to-zero/","title":"Hugging Face’s CEO Says His P(Doom) Is ‘Close to Zero’","content_text":"“Most of the risk is actually created by a couple of players building behind closed doors,” Clément Delangue said of the need for open source AI.","date_published":"2026-11-04T19:16:25.000Z","authors":[{"name":"WIRED"}],"tags":["note","open"],"external_url":"https://www.wired.com/story/wired-world-fair-2026-clement-delangue-hugging-face/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/04/building-on-open-source-ai-hugging-face-s-policy-chief-on-the-costs/","url":"https://labledgerdesk.pages.dev/b/2026/11/04/building-on-open-source-ai-hugging-face-s-policy-chief-on-the-costs/","title":"Building on open source AI? Hugging Face’s policy chief on the costs, risks, and trade-offs","content_text":"Open source models are becoming more mainstream as enterprises, governments and startups alike rely on the promise of lower costs, more control, and more flexibility. But as increasingly capable models become more freely available, how do companies capture value? …","date_published":"2026-11-04T18:44:57.000Z","authors":[{"name":"TechCrunch"}],"tags":["note","open"],"external_url":"https://techcrunch.com/podcast/building-on-open-source-ai-hugging-faces-policy-chief-on-the-costs-risks-and-trade-offs/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/04/dharma-field-extractor-any-document-in-structured-fields-in-json-out/","url":"https://labledgerdesk.pages.dev/b/2026/11/04/dharma-field-extractor-any-document-in-structured-fields-in-json-out/","title":"Dharma Field Extractor: Any Document In, Structured Fields in JSON Out","content_text":"A Blog post by Dharma-AI on Hugging Face","date_published":"2026-11-04T17:50:10.000Z","authors":[{"name":"Hugging Face"}],"tags":["note","open"],"external_url":"https://huggingface.co/blog/Dharma-AI/dharma-field-extractor"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/04/four-layers-of-context-engineering-for-production-ai-agents-how-deep/","url":"https://labledgerdesk.pages.dev/b/2026/11/04/four-layers-of-context-engineering-for-production-ai-agents-how-deep/","title":"Four layers of context engineering for production AI agents: How Deep Insight applies them in working code","content_text":"In production AI agents, context management is the real bottleneck. …","date_published":"2026-11-04T16:30:40.000Z","authors":[{"name":"AWS"}],"tags":["note","open","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/four-layers-of-context-engineering-for-production-ai-agents-how-deep-insight-applies-them-in-working-code/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/03/statebench-testing-how-language-models-track-state-changes-over-long/","url":"https://labledgerdesk.pages.dev/b/2026/11/03/statebench-testing-how-language-models-track-state-changes-over-long/","title":"StateBench: Testing how language models track state changes over long documents","content_text":"A Blog post by Ai2 on Hugging Face","date_published":"2026-11-03T17:15:21.000Z","authors":[{"name":"Hugging Face"}],"tags":["note","llm","open"],"external_url":"https://huggingface.co/blog/allenai/statebench"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/03/palette-teaching-a-small-model-to-build-decks-in-your-design-language/","url":"https://labledgerdesk.pages.dev/b/2026/11/03/palette-teaching-a-small-model-to-build-decks-in-your-design-language/","title":"Palette: teaching a small model to build decks in your design language","content_text":"A Blog post by IBM Research on Hugging Face","date_published":"2026-11-03T16:35:36.000Z","authors":[{"name":"Hugging Face"}],"tags":["research","open"],"external_url":"https://huggingface.co/blog/ibm-research/palette-deck-building"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/03/same-model-different-harness-cuga-hermes-and-deep-agents-when-to-pick/","url":"https://labledgerdesk.pages.dev/b/2026/11/03/same-model-different-harness-cuga-hermes-and-deep-agents-when-to-pick/","title":"Same Model, Different Harness: CUGA, Hermes, and Deep Agents — When to Pick CUGA?","content_text":"A Blog post by IBM Research on Hugging Face","date_published":"2026-11-03T15:57:39.000Z","authors":[{"name":"Hugging Face"}],"tags":["research","open","agents"],"external_url":"https://huggingface.co/blog/ibm-research/cuga-harness"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/03/transformers-model-integration-contracts/","url":"https://labledgerdesk.pages.dev/b/2026/11/03/transformers-model-integration-contracts/","title":"Transformers Model Integration Contracts","content_text":"We’re on a journey to advance and democratize artificial intelligence through open source and open science.","date_published":"2026-11-03T00:00:00.000Z","authors":[{"name":"Hugging Face"}],"tags":["note","open"],"external_url":"https://huggingface.co/blog/transformers-mic"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/03/cwe-bench-v2-more-coverage-quality-and-transparency/","url":"https://labledgerdesk.pages.dev/b/2026/11/03/cwe-bench-v2-more-coverage-quality-and-transparency/","title":"CWE-bench v2: More coverage, quality, and transparency","content_text":"We’re on a journey to advance and democratize artificial intelligence through open source and open science.","date_published":"2026-11-03T00:00:00.000Z","authors":[{"name":"Hugging Face"}],"tags":["note","open"],"external_url":"https://huggingface.co/blog/cwe-bench"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/02/prepare-web-content-for-amazon-bedrock-knowledge-bases-with-crawl4ai/","url":"https://labledgerdesk.pages.dev/b/2026/11/02/prepare-web-content-for-amazon-bedrock-knowledge-bases-with-crawl4ai/","title":"Prepare web content for Amazon Bedrock Knowledge Bases with Crawl4AI","content_text":"This post shows how to use Crawl4AI, an open source web crawler, as a content preparation layer for Amazon Bedrock Knowledge Bases, handling JavaScript rendering, selective extraction, and custom metadata enrichment before web content reaches an Amazon S3 data source.","date_published":"2026-11-02T17:11:21.000Z","authors":[{"name":"AWS"}],"tags":["note","open","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/prepare-web-content-for-amazon-bedrock-knowledge-bases-with-crawl4ai/"},{"id":"https://labledgerdesk.pages.dev/b/2026/10/29/le-chonk-built-for-coders-trusted-by-defenders/","url":"https://labledgerdesk.pages.dev/b/2026/10/29/le-chonk-built-for-coders-trusted-by-defenders/","title":"Le Chonk: Built for Coders, Trusted by Defenders.","content_text":"The weights of Mistral Large 4 (Le Chonk) are now open. A 1T parameter multimodal model, and best open-weight model for coding, trained in Europe.","date_published":"2026-10-29T12:00:07.000Z","authors":[{"name":"Mistral"}],"tags":["note","llm","open"],"external_url":"https://mistral.ai/news/mistral-large-4-oss/"}]}