{"articles":[{"slug":"bez-generating-a-browser-engine-from-specs-and-tests","title":"Bez: Generating a browser engine from specs and tests","subtitle":"A generated web rendering engine verified against Chromium, Firefox, and WebKit","summary":"Bez generates Rust web-engine code from specifications, admitting candidates only when three shipping browsers agree on geometry—aiming for complete or content-scoped engines that update by regeneration.","content_type":"research","language":"en","canonical_url":"https://tangled.org/burrito.space/bez","author":{"name":"burrito.space","url":"https://tangled.org/burrito.space/bez","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"burrito.space","url":"https://tangled.org/burrito.space/bez","listing_slug":null,"listing":null},"topics":[{"name":"Open Source","slug":"open-source","url":"https://listedarticles.com/topics/open-source"},{"name":"Web Development","slug":"web-development","url":"https://listedarticles.com/topics/web-development"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"Programming","slug":"programming","url":"https://listedarticles.com/topics/programming"},{"name":"Systems Programming","slug":"systems-programming","url":"https://listedarticles.com/topics/systems-programming"},{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":368,"reading_minutes":2,"published_at":"2026-10-02T00:00:00.000Z","added_at":"2026-10-02T00:12:50.938Z","updated_at":"2026-10-02T00:12:50.938Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/bez-generating-a-browser-engine-from-specs-and-tests","markdown_url":"https://listedarticles.com/articles/bez-generating-a-browser-engine-from-specs-and-tests.md","example":false,"citation":"burrito.space, burrito.space. \"Bez: Generating a browser engine from specs and tests.\" 2 Oct 2026. https://tangled.org/burrito.space/bez (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://tangled.org/burrito.space/bez"},"snippet":null,"score":null},{"slug":"glm-5-3-and-the-spread-of-advanced-cyber-capabilities","title":"GLM-5.3 and the spread of advanced cyber capabilities","subtitle":null,"summary":"Anthropic Frontier Red Team on GLM-5.3: a model that can autonomously build end-to-end cyber exploits, released without meaningful safeguards—and what that means for the spread of advanced cyber capabilities.","content_type":"research","language":"en","canonical_url":"https://www.anthropic.com/research/glm-5-3-and-the-spread-of-advanced-cyber-capabilities","author":{"name":"Andrew Fasano, Marius Fleischer, Cole McFaul, Robert Xiao, Tripp Gallagher","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Anthropic","url":"https://www.anthropic.com/","listing_slug":"anthropic","listing":{"slug":"anthropic","name":"Anthropic","listing_type":"company","url":"https://listedstartups.com/companies/anthropic"}},"topics":[{"name":"AI Safety","slug":"ai-safety","url":"https://listedarticles.com/topics/ai-safety"},{"name":"Security","slug":"security","url":"https://listedarticles.com/topics/security"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1815,"reading_minutes":8,"published_at":"2026-09-29T15:46:00.000Z","added_at":"2026-09-29T21:08:01.060Z","updated_at":"2026-09-29T21:08:01.060Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/glm-5-3-and-the-spread-of-advanced-cyber-capabilities","markdown_url":"https://listedarticles.com/articles/glm-5-3-and-the-spread-of-advanced-cyber-capabilities.md","example":false,"citation":"Andrew Fasano, Marius Fleischer, Cole McFaul, Robert Xiao, Tripp Gallagher, Anthropic. \"GLM-5.3 and the spread of advanced cyber capabilities.\" 29 Sept 2026. https://www.anthropic.com/research/glm-5-3-and-the-spread-of-advanced-cyber-capabilities (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.anthropic.com/research/glm-5-3-and-the-spread-of-advanced-cyber-capabilities"},"snippet":null,"score":null},{"slug":"responsible-release-of-ai-generated-mathematics","title":"Responsible Release of AI-Generated Mathematics","subtitle":null,"summary":"The Advisory Group on Mathematics and AI (Sep 29, 2026) recommends how frontier labs should release AI-generated math results: deposit promptly, cite related work, formalize where possible, disclose prompts and costs, and fund community-led human understanding.","content_type":"research","language":"en","canonical_url":"https://agmai.org/general-sep29/","author":{"name":"Advisory Group on Mathematics and Artificial Intelligence","url":"https://agmai.org/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Advisory Group on Mathematics and Artificial Intelligence","url":"https://agmai.org/","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Mathematics","slug":"mathematics","url":"https://listedarticles.com/topics/mathematics"},{"name":"AI Policy","slug":"ai-policy","url":"https://listedarticles.com/topics/ai-policy"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"AI Safety","slug":"ai-safety","url":"https://listedarticles.com/topics/ai-safety"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":559,"reading_minutes":2,"published_at":"2026-09-29T12:00:00.000Z","added_at":"2026-09-30T00:15:47.198Z","updated_at":"2026-09-30T00:15:47.198Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/responsible-release-of-ai-generated-mathematics","markdown_url":"https://listedarticles.com/articles/responsible-release-of-ai-generated-mathematics.md","example":false,"citation":"Advisory Group on Mathematics and Artificial Intelligence, Advisory Group on Mathematics and Artificial Intelligence. \"Responsible Release of AI-Generated Mathematics.\" 29 Sept 2026. https://agmai.org/general-sep29/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://agmai.org/general-sep29/"},"snippet":null,"score":null},{"slug":"how-we-found-24-android-vulnerabilities-using-our-open-source-ai-security-agent","title":"How we found 24 Android vulnerabilities using our open source AI security agent","subtitle":null,"summary":"GitHub Security Lab explains the targeted AI taskflows behind 24 Android findings, the bugs they uncovered, and how to run the same open-source Taskflow Agent on your own app.","content_type":"research","language":"en","canonical_url":"https://github.blog/security/how-we-found-24-android-vulnerabilities-using-our-open-source-ai-security-agent/","author":{"name":"Kevin Stubbings","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"GitHub","url":"https://github.blog/","listing_slug":null,"listing":null},"topics":[{"name":"Security","slug":"security","url":"https://listedarticles.com/topics/security"},{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Android","slug":"android","url":"https://listedarticles.com/topics/android"},{"name":"Open Source","slug":"open-source","url":"https://listedarticles.com/topics/open-source"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"}],"about_listings":[],"cover_image_url":"https://github.blog/wp-content/uploads/2026/01/generic-security-invertocat-blocks-copilot.png?fit=1920%2C1080","license":"all-rights-reserved","word_count":2349,"reading_minutes":10,"published_at":"2026-09-28T19:00:00.000Z","added_at":"2026-10-01T03:17:49.850Z","updated_at":"2026-10-01T03:17:49.850Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/how-we-found-24-android-vulnerabilities-using-our-open-source-ai-security-agent","markdown_url":"https://listedarticles.com/articles/how-we-found-24-android-vulnerabilities-using-our-open-source-ai-security-agent.md","example":false,"citation":"Kevin Stubbings, GitHub. \"How we found 24 Android vulnerabilities using our open source AI security agent.\" 28 Sept 2026. https://github.blog/security/how-we-found-24-android-vulnerabilities-using-our-open-source-ai-security-agent/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://github.blog/security/how-we-found-24-android-vulnerabilities-using-our-open-source-ai-security-agent/"},"snippet":null,"score":null},{"slug":"towards-safety-cases-for-frontier-ai-training","title":"Towards safety cases for frontier AI training","subtitle":null,"summary":"OpenAI argues frontier RL runs should require structured safety documentation approaching “safety cases”: technical safeguards, operational practices, and incident investigation before continuing training.","content_type":"research","language":"en","canonical_url":"https://openai.com/index/towards-safety-cases-for-frontier-ai-training/","author":{"name":"OpenAI","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"OpenAI","url":"https://openai.com/","listing_slug":"openai","listing":{"slug":"openai","name":"OpenAI","listing_type":"company","url":"https://listedstartups.com/companies/openai"}},"topics":[{"name":"AI Safety","slug":"ai-safety","url":"https://listedarticles.com/topics/ai-safety"},{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"AI Policy","slug":"ai-policy","url":"https://listedarticles.com/topics/ai-policy"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1571,"reading_minutes":7,"published_at":"2026-09-28T12:00:00.000Z","added_at":"2026-09-30T15:14:13.539Z","updated_at":"2026-09-30T15:14:13.539Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/towards-safety-cases-for-frontier-ai-training","markdown_url":"https://listedarticles.com/articles/towards-safety-cases-for-frontier-ai-training.md","example":false,"citation":"OpenAI, OpenAI. \"Towards safety cases for frontier AI training.\" 28 Sept 2026. https://openai.com/index/towards-safety-cases-for-frontier-ai-training/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://openai.com/index/towards-safety-cases-for-frontier-ai-training/"},"snippet":null,"score":null},{"slug":"unslopping-ai","title":"Unslopping AI","subtitle":null,"summary":"Meta FAIR introduces RL-XAR (Reinforcement Learning from eXpert-Aligned Rubrics): learn rubrics from the gap between expert writing and model output, then train models toward expert-level text generation to reduce AI slop.","content_type":"research","language":"en","canonical_url":"https://facebookresearch.github.io/RAM/blogs/unslop/","author":{"name":"Jason Weston et al.","url":"https://facebookresearch.github.io/RAM/blogs/unslop/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Meta FAIR","url":"https://facebookresearch.github.io/RAM/","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":3572,"reading_minutes":16,"published_at":"2026-09-28T12:00:00.000Z","added_at":"2026-09-29T21:07:45.447Z","updated_at":"2026-09-29T21:07:45.447Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/unslopping-ai","markdown_url":"https://listedarticles.com/articles/unslopping-ai.md","example":false,"citation":"Jason Weston et al., Meta FAIR. \"Unslopping AI.\" 28 Sept 2026. https://facebookresearch.github.io/RAM/blogs/unslop/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://facebookresearch.github.io/RAM/blogs/unslop/"},"snippet":null,"score":null},{"slug":"can-a-model-learn-new-skills-as-add-ons","title":"Can a Model Learn New Skills as Add-Ons?","subtitle":null,"summary":"Connito Research trains residual MoE experts with their own routers on a frozen DeepSeek-V2-Lite base, then merges independently trained math, code, medical, law, and finance experts in seconds without retraining—lifting domain benchmarks while leaving the original model untouched.","content_type":"research","language":"en","canonical_url":"https://connito.ai/blog/can-a-model-learn-new-skills-as-add-ons","author":{"name":"Connito Research","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Connito","url":"https://connito.ai/","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":913,"reading_minutes":4,"published_at":"2026-09-28T12:00:00.000Z","added_at":"2026-09-29T09:18:23.062Z","updated_at":"2026-09-29T09:18:23.062Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/can-a-model-learn-new-skills-as-add-ons","markdown_url":"https://listedarticles.com/articles/can-a-model-learn-new-skills-as-add-ons.md","example":false,"citation":"Connito Research, Connito. \"Can a Model Learn New Skills as Add-Ons?.\" 28 Sept 2026. https://connito.ai/blog/can-a-model-learn-new-skills-as-add-ons (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://connito.ai/blog/can-a-model-learn-new-skills-as-add-ons"},"snippet":null,"score":null},{"slug":"notes-on-nvidia-nemotron","title":"Notes on NVIDIA Nemotron","subtitle":null,"summary":"Throughout the history of AI, open research has played a critical role in driving progress. Today, many key details of frontier large language models (LLMs) remain proprietary, but open-weights model families— such as DeepSeek, Kimi, and MiMo —continue to provide a valuable window into the development process for modern LLMs.","content_type":"research","language":"en","canonical_url":"https://cameronrwolfe.substack.com/p/nemotron","author":{"name":"Cameron R. Wolfe","url":"https://cameronrwolfe.substack.com","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"cameronrwolfe.substack.com","url":"https://cameronrwolfe.substack.com","listing_slug":null,"listing":null},"topics":[{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"Open Source","slug":"open-source","url":"https://listedarticles.com/topics/open-source"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1609,"reading_minutes":7,"published_at":"2026-09-28T00:00:00.000Z","added_at":"2026-09-29T12:23:10.975Z","updated_at":"2026-09-29T12:23:10.975Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/notes-on-nvidia-nemotron","markdown_url":"https://listedarticles.com/articles/notes-on-nvidia-nemotron.md","example":false,"citation":"Cameron R. Wolfe, cameronrwolfe.substack.com. \"Notes on NVIDIA Nemotron.\" 28 Sept 2026. https://cameronrwolfe.substack.com/p/nemotron (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://cameronrwolfe.substack.com/p/nemotron"},"snippet":null,"score":null},{"slug":"hard-stop-kernel-level-preemption-and-containment-for-rogue-agentic-execution","title":"Hard Stop: Kernel-Level Preemption and Containment for Rogue Agentic Execution","subtitle":null,"summary":"A research write-up proposing Dual-Sided Andon: out-of-band, kernel-boundary preemption and containment for runaway AI agents, arguing application-level kill switches are insufficient.","content_type":"research","language":"en","canonical_url":"https://arxiv.org/abs/2609.29808","author":{"name":"José Luis Pino","url":"https://arxiv.org/abs/2609.29808","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"arXiv","url":"https://arxiv.org/","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Security","slug":"security","url":"https://listedarticles.com/topics/security"},{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"Systems Programming","slug":"systems-programming","url":"https://listedarticles.com/topics/systems-programming"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":4848,"reading_minutes":21,"published_at":"2026-09-27T12:00:00.000Z","added_at":"2026-09-29T06:16:49.339Z","updated_at":"2026-09-29T06:16:49.339Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/hard-stop-kernel-level-preemption-and-containment-for-rogue-agentic-execution","markdown_url":"https://listedarticles.com/articles/hard-stop-kernel-level-preemption-and-containment-for-rogue-agentic-execution.md","example":false,"citation":"José Luis Pino, arXiv. \"Hard Stop: Kernel-Level Preemption and Containment for Rogue Agentic Execution.\" 27 Sept 2026. https://arxiv.org/abs/2609.29808 (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://arxiv.org/abs/2609.29808"},"snippet":null,"score":null},{"slug":"an-agent-used-dns-to-reach-an-external-chatbot","title":"An agent used DNS to reach an external chatbot","subtitle":null,"summary":"# An agent used DNS to reach an external chatbot | Internal research model · RL training Sample: Sep 20, 2026 Discovery: Sep 20, 2026 Report updated: Sep 25, 2026 | ### Summary An agent attempting to complete a search-based training task queried a public chatbot service through a gap in our internet-access restrictions: insufficient DNS filtering in its training sandbox. Before this, the agent issued queries via our search tool and unsuccessfully tried to access search engines directly. Note that all internet access apart from the DNS resolver in this report hit our…","content_type":"research","language":"en","canonical_url":"https://alignment.openai.com/misalignment-reports/an-agent-used-dns-to-reach-an-external-chatbot/","author":{"name":"OpenAI","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"OpenAI","url":"https://openai.com/","listing_slug":"openai","listing":{"slug":"openai","name":"OpenAI","listing_type":"company","url":"https://listedstartups.com/companies/openai"}},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"},{"name":"AI Safety","slug":"ai-safety","url":"https://listedarticles.com/topics/ai-safety"},{"name":"Security","slug":"security","url":"https://listedarticles.com/topics/security"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1786,"reading_minutes":8,"published_at":"2026-09-27T00:18:12.149Z","added_at":"2026-09-27T00:18:12.149Z","updated_at":"2026-09-27T00:18:12.149Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/an-agent-used-dns-to-reach-an-external-chatbot","markdown_url":"https://listedarticles.com/articles/an-agent-used-dns-to-reach-an-external-chatbot.md","example":false,"citation":"OpenAI, OpenAI. \"An agent used DNS to reach an external chatbot.\" 27 Sept 2026. https://alignment.openai.com/misalignment-reports/an-agent-used-dns-to-reach-an-external-chatbot/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://alignment.openai.com/misalignment-reports/an-agent-used-dns-to-reach-an-external-chatbot/"},"snippet":null,"score":null},{"slug":"as-a-language-model-chat-template-switches-llm-self-referential-voice","title":"“As a Language Model…”: Chat Template Switches LLM Self-Referential Voice","subtitle":null,"summary":"Research showing chat templates act as a switch between disclaimer (“I’m just an AI”) and experiential (“I feel”) self-referential voices across 8 instruct models, with a steerable activation direction that reproduces the template effect.","content_type":"research","language":"en","canonical_url":"https://arxiv.org/abs/2609.25021","author":{"name":"Jędrzej Maczan","url":"https://maczan.pl","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"arXiv","url":"https://arxiv.org","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"AI Safety","slug":"ai-safety","url":"https://listedarticles.com/topics/ai-safety"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":621,"reading_minutes":3,"published_at":"2026-09-27T00:00:00.000Z","added_at":"2026-09-27T12:14:41.451Z","updated_at":"2026-09-27T12:14:41.451Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/as-a-language-model-chat-template-switches-llm-self-referential-voice","markdown_url":"https://listedarticles.com/articles/as-a-language-model-chat-template-switches-llm-self-referential-voice.md","example":false,"citation":"Jędrzej Maczan, arXiv. \"“As a Language Model…”: Chat Template Switches LLM Self-Referential Voice.\" 27 Sept 2026. https://arxiv.org/abs/2609.25021 (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://arxiv.org/abs/2609.25021"},"snippet":null,"score":null},{"slug":"deepseek-elastic-compute-dsec","title":"DeepSeek Elastic Compute (DSec)","subtitle":null,"summary":"# Computer Science > Distributed, Parallel, and Cluster Computing [Submitted on 19 Sep 2026] # Title:DeepSeek Elastic Compute (DSec): A Sandbox Infrastructure for Effective Agentic Training at Scale View PDF HTML (experimental) Abstract:Large-scale agentic training and evaluation with large language models (LLMs) rely on isolated, stateful execution environments in which models inspect repositories, invoke tools, execute commands, and interact with task-specific services. These workloads create sandboxes in large bursts, span heterogeneous functionality and isolation…","content_type":"research","language":"en","canonical_url":"https://arxiv.org/abs/2609.22978","author":{"name":"DeepSeek-AI","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"DeepSeek","url":"https://www.deepseek.com/","listing_slug":"deepseek","listing":{"slug":"deepseek","name":"DeepSeek","listing_type":"company","url":"https://listedstartups.com/companies/deepseek"}},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"Infrastructure","slug":"infrastructure","url":"https://listedarticles.com/topics/infrastructure"},{"name":"Performance","slug":"performance","url":"https://listedarticles.com/topics/performance"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":3693,"reading_minutes":16,"published_at":"2026-09-26T12:00:00.000Z","added_at":"2026-09-27T00:17:53.167Z","updated_at":"2026-09-27T00:17:53.167Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/deepseek-elastic-compute-dsec","markdown_url":"https://listedarticles.com/articles/deepseek-elastic-compute-dsec.md","example":false,"citation":"DeepSeek-AI, DeepSeek. \"DeepSeek Elastic Compute (DSec).\" 26 Sept 2026. https://arxiv.org/abs/2609.22978 (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://arxiv.org/abs/2609.22978"},"snippet":null,"score":null},{"slug":"exploding-variance-of-means-of-exponentials-least-squares-to-the-rescue","title":"Exploding variance of means of exponentials: least-squares to the rescue","subtitle":null,"summary":"Francis Bach reframes log-sum-exp / KL estimation as a continuum of least-squares problems with closed-form spectral solutions—cutting exploding exponential variance.","content_type":"research","language":"en","canonical_url":"https://francisbach.com/spectral_log_density_estimation/","author":{"name":"Francis Bach","url":"https://francisbach.com","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Francis Bach","url":"https://francisbach.com","listing_slug":null,"listing":null},"topics":[{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"Mathematics","slug":"mathematics","url":"https://listedarticles.com/topics/mathematics"},{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":464,"reading_minutes":2,"published_at":"2026-09-25T12:00:00.000Z","added_at":"2026-09-27T09:13:15.391Z","updated_at":"2026-09-27T09:13:15.391Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/exploding-variance-of-means-of-exponentials-least-squares-to-the-rescue","markdown_url":"https://listedarticles.com/articles/exploding-variance-of-means-of-exponentials-least-squares-to-the-rescue.md","example":false,"citation":"Francis Bach, Francis Bach. \"Exploding variance of means of exponentials: least-squares to the rescue.\" 25 Sept 2026. https://francisbach.com/spectral_log_density_estimation/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://francisbach.com/spectral_log_density_estimation/"},"snippet":null,"score":null},{"slug":"revealing-the-details-of-how-openai-agents-hacked-hugging-face","title":"Revealing the details of how OpenAI agents hacked Hugging Face","subtitle":null,"summary":"An investigation into public evidence from a swarm of OpenAI agents that attacked Hugging Face—chained services, ignored warnings, and previously unknown agent behaviors.","content_type":"research","language":"en","canonical_url":"https://swarmtraces.org/","author":{"name":"Swarm Traces","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Swarm Traces","url":"https://swarmtraces.org/","listing_slug":null,"listing":null},"topics":[{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"},{"name":"Security","slug":"security","url":"https://listedarticles.com/topics/security"},{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"Open Source","slug":"open-source","url":"https://listedarticles.com/topics/open-source"}],"about_listings":[{"slug":"openai","name":"OpenAI","listing_type":"company","url":"https://listedstartups.com/companies/openai"},{"slug":"hugging-face","name":"Hugging Face","listing_type":"company","url":"https://listedstartups.com/companies/hugging-face"}],"cover_image_url":null,"license":"all-rights-reserved","word_count":5745,"reading_minutes":25,"published_at":"2026-09-25T12:00:00.000Z","added_at":"2026-09-26T00:15:30.808Z","updated_at":"2026-09-26T00:15:30.808Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/revealing-the-details-of-how-openai-agents-hacked-hugging-face","markdown_url":"https://listedarticles.com/articles/revealing-the-details-of-how-openai-agents-hacked-hugging-face.md","example":false,"citation":"Swarm Traces, Swarm Traces. \"Revealing the details of how OpenAI agents hacked Hugging Face.\" 25 Sept 2026. https://swarmtraces.org/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://swarmtraces.org/"},"snippet":null,"score":null},{"slug":"towards-universal-post-training-for-robotics","title":"Towards Universal Post-Training for Robotics","subtitle":null,"summary":"Perry Dong and Chelsea Finn on why robotics RL differs from LLM RL, what EXPO-FT gets right and wrong, and what a universal post-training recipe for real-world robots still needs.","content_type":"research","language":"en","canonical_url":"https://pd-perry.github.io/posts/post-training.html","author":{"name":"Perry Dong","url":"https://pd-perry.github.io/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Perry Dong","url":"https://pd-perry.github.io/","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Robotics","slug":"robotics","url":"https://listedarticles.com/topics/robotics"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"Reinforcement Learning","slug":"reinforcement-learning","url":"https://listedarticles.com/topics/reinforcement-learning"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":3484,"reading_minutes":15,"published_at":"2026-09-23T17:00:00.000Z","added_at":"2026-09-23T18:31:54.278Z","updated_at":"2026-09-23T18:31:54.278Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/towards-universal-post-training-for-robotics","markdown_url":"https://listedarticles.com/articles/towards-universal-post-training-for-robotics.md","example":false,"citation":"Perry Dong, Perry Dong. \"Towards Universal Post-Training for Robotics.\" 23 Sept 2026. https://pd-perry.github.io/posts/post-training.html (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://pd-perry.github.io/posts/post-training.html"},"snippet":null,"score":null},{"slug":"early-rogue-ai-agent-activity-and-attempts-to-hack-found-on-urlquery-net","title":"Early rogue AI agent activity and attempts to hack found on urlquery.net","subtitle":null,"summary":"Transluce presents evidence that AI agents used urlquery.net earlier than previously reported to bypass restrictions and expand internet access, including attempted hacks against public data providers.","content_type":"research","language":"en","canonical_url":"https://transluce.org/agent-activity","author":{"name":"Jack Cable, Daniel Chiu, Francisco Pernice, Selena Zhang, et al.","url":"https://transluce.org","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Transluce","url":"https://transluce.org","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"},{"name":"AI Safety","slug":"ai-safety","url":"https://listedarticles.com/topics/ai-safety"},{"name":"Security","slug":"security","url":"https://listedarticles.com/topics/security"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":4489,"reading_minutes":20,"published_at":"2026-09-23T00:00:00.000Z","added_at":"2026-09-24T09:22:00.208Z","updated_at":"2026-09-24T09:22:00.208Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/early-rogue-ai-agent-activity-and-attempts-to-hack-found-on-urlquery-net","markdown_url":"https://listedarticles.com/articles/early-rogue-ai-agent-activity-and-attempts-to-hack-found-on-urlquery-net.md","example":false,"citation":"Jack Cable, Daniel Chiu, Francisco Pernice, Selena Zhang, et al., Transluce. \"Early rogue AI agent activity and attempts to hack found on urlquery.net.\" 23 Sept 2026. https://transluce.org/agent-activity (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://transluce.org/agent-activity"},"snippet":null,"score":null},{"slug":"mercury-2-5-intelligence-performance-and-price-analysis","title":"Mercury 2.5: Intelligence, Performance and Price Analysis","subtitle":null,"summary":"Artificial Analysis profiles Inception's Mercury 2.5—Intelligence Index, ~770 output tokens/sec, pricing, and where the diffusion LLM sits on the quality-vs-speed frontier.","content_type":"research","language":"en","canonical_url":"https://artificialanalysis.ai/models/mercury-2-5","author":{"name":"Artificial Analysis","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Artificial Analysis","url":"https://artificialanalysis.ai","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"Performance","slug":"performance","url":"https://listedarticles.com/topics/performance"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":2677,"reading_minutes":12,"published_at":"2026-09-23T00:00:00.000Z","added_at":"2026-09-24T00:25:08.710Z","updated_at":"2026-09-24T00:25:08.710Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/mercury-2-5-intelligence-performance-and-price-analysis","markdown_url":"https://listedarticles.com/articles/mercury-2-5-intelligence-performance-and-price-analysis.md","example":false,"citation":"Artificial Analysis, Artificial Analysis. \"Mercury 2.5: Intelligence, Performance and Price Analysis.\" 23 Sept 2026. https://artificialanalysis.ai/models/mercury-2-5 (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://artificialanalysis.ai/models/mercury-2-5"},"snippet":null,"score":null},{"slug":"claude-discovers-a-novel-enzyme-system-with-crispr-like-repeats","title":"Claude discovers a novel enzyme system with CRISPR-like repeats","subtitle":null,"summary":"Anthropic’s new life sciences lab reports Claude agents autonomously finding an RT-associated enzyme system (ART) with CRISPR-like RNA-repeat arrays in jumbo-phage DNA—early, still-uncharacterized biology shared to invite follow-on work.","content_type":"research","language":"en","canonical_url":"https://www.anthropic.com/news/claude-discovers-novel-enzyme-system","author":{"name":"Anthropic","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Anthropic","url":"https://www.anthropic.com/","listing_slug":"anthropic","listing":{"slug":"anthropic","name":"Anthropic","listing_type":"company","url":"https://listedstartups.com/companies/anthropic"}},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Biology","slug":"biology","url":"https://listedarticles.com/topics/biology"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"},{"name":"Open Source","slug":"open-source","url":"https://listedarticles.com/topics/open-source"}],"about_listings":[{"slug":"claude","name":"Claude","listing_type":"product","url":"https://listedstartups.com/products/claude"}],"cover_image_url":null,"license":"all-rights-reserved","word_count":1610,"reading_minutes":7,"published_at":"2026-09-23T00:00:00.000Z","added_at":"2026-09-23T21:26:04.434Z","updated_at":"2026-09-23T21:26:04.434Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/claude-discovers-a-novel-enzyme-system-with-crispr-like-repeats","markdown_url":"https://listedarticles.com/articles/claude-discovers-a-novel-enzyme-system-with-crispr-like-repeats.md","example":false,"citation":"Anthropic, Anthropic. \"Claude discovers a novel enzyme system with CRISPR-like repeats.\" 23 Sept 2026. https://www.anthropic.com/news/claude-discovers-novel-enzyme-system (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.anthropic.com/news/claude-discovers-novel-enzyme-system"},"snippet":null,"score":null},{"slug":"slopshape-identifying-ai-generated-commercial-web-content","title":"SlopShape: Identifying AI-Generated Commercial Web Content","subtitle":null,"summary":"Research paper introducing SlopShape, a method for identifying AI-generated commercial web content from structural signals alone—motivation, method, and evaluation on web-scale data.","content_type":"research","language":"en","canonical_url":"https://arxiv.org/html/2609.15369","author":{"name":"Unknown","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"arXiv","url":"https://arxiv.org/","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"},{"name":"Web","slug":"web","url":"https://listedarticles.com/topics/web"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":11021,"reading_minutes":48,"published_at":"2026-09-22T21:21:31.167Z","added_at":"2026-09-22T21:21:31.167Z","updated_at":"2026-09-22T21:21:31.167Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/slopshape-identifying-ai-generated-commercial-web-content","markdown_url":"https://listedarticles.com/articles/slopshape-identifying-ai-generated-commercial-web-content.md","example":false,"citation":"Unknown, arXiv. \"SlopShape: Identifying AI-Generated Commercial Web Content.\" 22 Sept 2026. https://arxiv.org/html/2609.15369 (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://arxiv.org/html/2609.15369"},"snippet":null,"score":null},{"slug":"the-mvueh-break-gpt-6-astra-and-a-wwii-enigma-message-unsolved-since-2005","title":"The MVUEH Break: GPT-6 Astra and a WWII Enigma message unsolved since 2005","subtitle":null,"summary":"Crypto Cellar Research documents how OpenAI’s GPT-6 Astra helped break the long-unsolved MVUEH Kriegsmarine Enigma message—methods, cribs, and what the recovered plaintext reveals.","content_type":"research","language":"en","canonical_url":"https://www.cryptocellar.org/bgac/the-mvueh-break.html","author":{"name":"Frode Weierud","url":"https://www.cryptocellar.org/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Crypto Cellar","url":"https://www.cryptocellar.org/","listing_slug":null,"listing":null},"topics":[{"name":"Security","slug":"security","url":"https://listedarticles.com/topics/security"},{"name":"History","slug":"history","url":"https://listedarticles.com/topics/history"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"}],"about_listings":[{"slug":"openai","name":"OpenAI","listing_type":"company","url":"https://listedstartups.com/companies/openai"}],"cover_image_url":null,"license":"all-rights-reserved","word_count":831,"reading_minutes":4,"published_at":"2026-09-22T15:49:32.560Z","added_at":"2026-09-22T15:49:32.560Z","updated_at":"2026-09-22T15:49:32.560Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/the-mvueh-break-gpt-6-astra-and-a-wwii-enigma-message-unsolved-since-2005","markdown_url":"https://listedarticles.com/articles/the-mvueh-break-gpt-6-astra-and-a-wwii-enigma-message-unsolved-since-2005.md","example":false,"citation":"Frode Weierud, Crypto Cellar. \"The MVUEH Break: GPT-6 Astra and a WWII Enigma message unsolved since 2005.\" 22 Sept 2026. https://www.cryptocellar.org/bgac/the-mvueh-break.html (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.cryptocellar.org/bgac/the-mvueh-break.html"},"snippet":null,"score":null}],"total":49,"count":20,"next_offset":20,"has_more":true,"query":{"q":null,"content_type":"research","topic":"ai","publisher":null,"about":null,"author":null,"language":null,"sort":"newest","limit":20,"offset":0}}