{"articles":[{"slug":"introducing-clef-our-open-source-decision-models-and-new-rl-fine-tuning-platform","title":"Introducing Clef: our open-source decision models, and new RL fine-tuning platform","subtitle":null,"summary":"We are introducing Clef and Clef-flash, open-source decision models hosted on Workers AI for high-speed classification and agentic workflows. Also launching: a new reinforcement learning platform that allows developers to fine-tune decision models using their own data.","content_type":"announcement","language":"en","canonical_url":"https://blog.cloudflare.com/clef-decision-models/","author":{"name":null,"url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Cloudflare","url":"https://www.cloudflare.com/","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":"Open Source","slug":"open-source","url":"https://listedarticles.com/topics/open-source"},{"name":"Cloudflare","slug":"cloudflare","url":"https://listedarticles.com/topics/cloudflare"},{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"}],"about_listings":[],"cover_image_url":"https://blog.cloudflare.com/_emdash/api/media/file/01M3TJV43SPQCPKJ6GBXFCDKNE.01M3TJV53VYDMVNCZDPH1FBFYN.png","license":"all-rights-reserved","word_count":2230,"reading_minutes":10,"published_at":"2026-10-01T15:34:02.111Z","added_at":"2026-10-01T18:09:51.856Z","updated_at":"2026-10-01T18:09:51.856Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/introducing-clef-our-open-source-decision-models-and-new-rl-fine-tuning-platform","markdown_url":"https://listedarticles.com/articles/introducing-clef-our-open-source-decision-models-and-new-rl-fine-tuning-platform.md","example":false,"citation":"Cloudflare. \"Introducing Clef: our open-source decision models, and new RL fine-tuning platform.\" 1 Oct 2026. https://blog.cloudflare.com/clef-decision-models/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://blog.cloudflare.com/clef-decision-models/"},"snippet":null,"score":null},{"slug":"what-makes-llm-tokenization-slow","title":"What Makes LLM Tokenization Slow?","subtitle":"Exploring the performance of byte-pair encoding by optimizing a GPT-2 tokenizer.","summary":"Andrew Healey dissects GPT-2’s reference BPE tokenizer, measures what makes tokenization slow, and shows concrete optimizations on the hot path of LLM products.","content_type":"tutorial","language":"en","canonical_url":"https://healeycodes.com/what-makes-llm-tokenization-slow","author":{"name":"Andrew Healey","url":"https://healeycodes.com/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"healeycodes","url":"https://healeycodes.com/","listing_slug":null,"listing":null},"topics":[{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Programming","slug":"programming","url":"https://listedarticles.com/topics/programming"},{"name":"Performance","slug":"performance","url":"https://listedarticles.com/topics/performance"},{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":2547,"reading_minutes":11,"published_at":"2026-10-01T12:11:08.585Z","added_at":"2026-10-01T12:11:08.585Z","updated_at":"2026-10-01T12:11:08.585Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/what-makes-llm-tokenization-slow","markdown_url":"https://listedarticles.com/articles/what-makes-llm-tokenization-slow.md","example":false,"citation":"Andrew Healey, healeycodes. \"What Makes LLM Tokenization Slow?.\" 1 Oct 2026. https://healeycodes.com/what-makes-llm-tokenization-slow (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://healeycodes.com/what-makes-llm-tokenization-slow"},"snippet":null,"score":null},{"slug":"context-management-is-an-underrated-habit","title":"Context management is an underrated habit","subtitle":null,"summary":"How you manage context in a Claude Code session has a direct effect on both your token bill and the quality of what you get back. Do it well and you spend less for better work. An efficient session gives Claude the context it needs to finish the job while removing context that has stopped being useful. That means starting with a lean setup, keeping investigations focused, and deliberately deciding when to continue, compact, or start again. Here are the context management techniques we use on the","content_type":"blog_post","language":"en","canonical_url":"https://ideas.fin.ai/p/context-management-is-an-underrated","author":{"name":"Akshay Katyal","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Fin","url":"https://fin.ai/","listing_slug":"fin","listing":{"slug":"fin","name":"Fin","listing_type":"product","url":"https://listedstartups.com/products/fin"}},"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":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Productivity","slug":"productivity","url":"https://listedarticles.com/topics/productivity"},{"name":"Developer Tools","slug":"developer-tools","url":"https://listedarticles.com/topics/developer-tools"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1257,"reading_minutes":5,"published_at":"2026-10-01T12:00:00.000Z","added_at":"2026-10-01T15:13:20.860Z","updated_at":"2026-10-01T15:13:20.860Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/context-management-is-an-underrated-habit","markdown_url":"https://listedarticles.com/articles/context-management-is-an-underrated-habit.md","example":false,"citation":"Akshay Katyal, Fin. \"Context management is an underrated habit.\" 1 Oct 2026. https://ideas.fin.ai/p/context-management-is-an-underrated (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://ideas.fin.ai/p/context-management-is-an-underrated"},"snippet":null,"score":null},{"slug":"the-dot-and-the-swarm","title":"The Dot and the Swarm","subtitle":"Benefitting from the Bitter Lesson","summary":"Ethan Mollick on what he underestimated most about AI progress: agents that self-organize into swarms, what that means for tools like Muse and Dots, and why we keep relearning the Bitter Lesson.","content_type":"essay","language":"en","canonical_url":"https://www.oneusefulthing.org/p/the-dot-and-the-swarm","author":{"name":"Ethan Mollick","url":"https://www.oneusefulthing.org/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"One Useful Thing","url":"https://www.oneusefulthing.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":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Opinion","slug":"opinion","url":"https://listedarticles.com/topics/opinion"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1891,"reading_minutes":8,"published_at":"2026-10-01T11:00:00.000Z","added_at":"2026-10-01T12:10:58.087Z","updated_at":"2026-10-01T12:10:58.087Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/the-dot-and-the-swarm","markdown_url":"https://listedarticles.com/articles/the-dot-and-the-swarm.md","example":false,"citation":"Ethan Mollick, One Useful Thing. \"The Dot and the Swarm.\" 1 Oct 2026. https://www.oneusefulthing.org/p/the-dot-and-the-swarm (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.oneusefulthing.org/p/the-dot-and-the-swarm"},"snippet":null,"score":null},{"slug":"claude-shaped-science","title":"Claude-shaped science","subtitle":"Working on Claude-shaped problems with BootLoops, a toolkit for exact calculations in quantitative science","summary":"Harvard physicist Matthew Schwartz’s Anthropic guest post on BootLoops: an open-source harness that steers LLMs toward checkable, quantitative “Claude-shaped” problems across physics, ecology, genetics, and more—with human experts supplying scientific taste.","content_type":"essay","language":"en","canonical_url":"https://www.anthropic.com/research/claude-shaped-science","author":{"name":"Matthew Schwartz","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":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"Science","slug":"science","url":"https://listedarticles.com/topics/science"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"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":[{"slug":"claude","name":"Claude","listing_type":"product","url":"https://listedstartups.com/products/claude"}],"cover_image_url":null,"license":"all-rights-reserved","word_count":1244,"reading_minutes":5,"published_at":"2026-10-01T00:00:00.000Z","added_at":"2026-10-02T03:18:31.443Z","updated_at":"2026-10-02T03:18:31.443Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/claude-shaped-science","markdown_url":"https://listedarticles.com/articles/claude-shaped-science.md","example":false,"citation":"Matthew Schwartz, Anthropic. \"Claude-shaped science.\" 1 Oct 2026. https://www.anthropic.com/research/claude-shaped-science (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.anthropic.com/research/claude-shaped-science"},"snippet":null,"score":null},{"slug":"using-opus-5-5-to-discover-a-new-eyewitness-record-of-the-dodo","title":"Using Opus 5.5 to discover a new eyewitness record of the dodo","subtitle":"Frontier models can now produce novel historical knowledge, but in a really weird way","summary":"Historian Benjamin Breen walks through how Opus 5.5 surfaced a previously unnoticed 1615 Dutch East India Company log mentioning dodos—and what AI archival sleuthing can and cannot yet do.","content_type":"essay","language":"en","canonical_url":"https://resobscura.substack.com/p/using-opus-55-to-discover-a-new-eyewitness","author":{"name":"Benjamin Breen","url":"https://resobscura.substack.com/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Res Obscura","url":"https://resobscura.substack.com/","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"History","slug":"history","url":"https://listedarticles.com/topics/history"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Science","slug":"science","url":"https://listedarticles.com/topics/science"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":631,"reading_minutes":3,"published_at":"2026-10-01T00:00:00.000Z","added_at":"2026-10-02T00:12:46.460Z","updated_at":"2026-10-02T00:12:46.460Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/using-opus-5-5-to-discover-a-new-eyewitness-record-of-the-dodo","markdown_url":"https://listedarticles.com/articles/using-opus-5-5-to-discover-a-new-eyewitness-record-of-the-dodo.md","example":false,"citation":"Benjamin Breen, Res Obscura. \"Using Opus 5.5 to discover a new eyewitness record of the dodo.\" 1 Oct 2026. https://resobscura.substack.com/p/using-opus-55-to-discover-a-new-eyewitness (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://resobscura.substack.com/p/using-opus-55-to-discover-a-new-eyewitness"},"snippet":null,"score":null},{"slug":"cut-your-ai-spend-with-ai-gateways-auto-router","title":"Cut your AI spend with AI Gateway's Auto Router","subtitle":null,"summary":"Cloudflare AI Gateway now features a model router that evaluates request complexity using an edge-deployed classifier to select the optimal model. By balancing expected output quality against token costs, organizations can dramatically cut AI spend while maintaining performance.","content_type":"announcement","language":"en","canonical_url":"https://blog.cloudflare.com/auto-router","author":{"name":null,"url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Cloudflare","url":"https://blog.cloudflare.com/","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":"Infrastructure","slug":"infrastructure","url":"https://listedarticles.com/topics/infrastructure"},{"name":"Performance","slug":"performance","url":"https://listedarticles.com/topics/performance"},{"name":"Developer Tools","slug":"developer-tools","url":"https://listedarticles.com/topics/developer-tools"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1627,"reading_minutes":7,"published_at":"2026-09-30T13:00:00.000Z","added_at":"2026-10-01T00:17:46.539Z","updated_at":"2026-10-01T00:17:46.539Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/cut-your-ai-spend-with-ai-gateways-auto-router","markdown_url":"https://listedarticles.com/articles/cut-your-ai-spend-with-ai-gateways-auto-router.md","example":false,"citation":"Cloudflare. \"Cut your AI spend with AI Gateway's Auto Router.\" 30 Sept 2026. https://blog.cloudflare.com/auto-router (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://blog.cloudflare.com/auto-router"},"snippet":null,"score":null},{"slug":"tokenization-a-survey-for-modern-nlp","title":"Tokenization: A Survey for Modern NLP","subtitle":null,"summary":"A comprehensive survey by 32+ tokenizer researchers covering subword algorithms, multilingual pitfalls, evaluation, theory, security, and alternatives—framing tokenization as a first-class bottleneck in the LLM era.","content_type":"research","language":"en","canonical_url":"https://www.alphaxiv.org/abs/2609.tokenization-survey-modern-nlp","author":{"name":"Marco Cognetta et al.","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"alphaXiv","url":"https://www.alphaxiv.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":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"},{"name":"NLP","slug":"nlp","url":"https://listedarticles.com/topics/nlp"},{"name":"Programming","slug":"programming","url":"https://listedarticles.com/topics/programming"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":376,"reading_minutes":2,"published_at":"2026-09-30T00:00:00.000Z","added_at":"2026-10-02T03:18:44.731Z","updated_at":"2026-10-02T03:18:44.731Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/tokenization-a-survey-for-modern-nlp","markdown_url":"https://listedarticles.com/articles/tokenization-a-survey-for-modern-nlp.md","example":false,"citation":"Marco Cognetta et al., alphaXiv. \"Tokenization: A Survey for Modern NLP.\" 30 Sept 2026. https://www.alphaxiv.org/abs/2609.tokenization-survey-modern-nlp (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.alphaxiv.org/abs/2609.tokenization-survey-modern-nlp"},"snippet":null,"score":null},{"slug":"q3-2026-smarter-routing-airside-and-realtime","title":"Q3 2026: Smarter Routing, Airside & Realtime","subtitle":"LLM Gateway product roundup — 50M requests and 1.805T tokens","summary":"LLM Gateway's Q3 2026 roundup: smart and cache-aware routing, Airside provider console, realtime voice, Lounge projects, coding-tool integrations, and stronger enterprise controls—with a public traffic snapshot.","content_type":"changelog","language":"en","canonical_url":"https://llmgateway.io/blog/q3-2026-roundup","author":{"name":"Ismail Ghallou","url":"https://llmgateway.io/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"LLM Gateway","url":"https://llmgateway.io/","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":"Infrastructure","slug":"infrastructure","url":"https://listedarticles.com/topics/infrastructure"},{"name":"Developer Tools","slug":"developer-tools","url":"https://listedarticles.com/topics/developer-tools"},{"name":"Announcements","slug":"announcements","url":"https://listedarticles.com/topics/announcements"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":285,"reading_minutes":1,"published_at":"2026-09-30T00:00:00.000Z","added_at":"2026-10-02T00:12:57.254Z","updated_at":"2026-10-02T00:12:57.254Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/q3-2026-smarter-routing-airside-and-realtime","markdown_url":"https://listedarticles.com/articles/q3-2026-smarter-routing-airside-and-realtime.md","example":false,"citation":"Ismail Ghallou, LLM Gateway. \"Q3 2026: Smarter Routing, Airside & Realtime.\" 30 Sept 2026. https://llmgateway.io/blog/q3-2026-roundup (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://llmgateway.io/blog/q3-2026-roundup"},"snippet":null,"score":null},{"slug":"hydrafusion-in-vs-code-and-the-github-copilot-app","title":"HydraFusion in VS Code and the GitHub Copilot app","subtitle":null,"summary":"The HydraFusion research preview is now available in Visual Studio Code and the GitHub Copilot app, expanding beyond Copilot CLI. HydraFusion appears in the model picker, but rather than being…","content_type":"changelog","language":"en","canonical_url":"https://github.blog/changelog/2026-09-30-hydrafusion-in-vs-code-and-the-github-copilot-app/","author":{"name":null,"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":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Developer Tools","slug":"developer-tools","url":"https://listedarticles.com/topics/developer-tools"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Programming","slug":"programming","url":"https://listedarticles.com/topics/programming"},{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":389,"reading_minutes":2,"published_at":"2026-09-30T00:00:00.000Z","added_at":"2026-10-01T00:17:40.801Z","updated_at":"2026-10-01T00:17:40.801Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/hydrafusion-in-vs-code-and-the-github-copilot-app","markdown_url":"https://listedarticles.com/articles/hydrafusion-in-vs-code-and-the-github-copilot-app.md","example":false,"citation":"GitHub. \"HydraFusion in VS Code and the GitHub Copilot app.\" 30 Sept 2026. https://github.blog/changelog/2026-09-30-hydrafusion-in-vs-code-and-the-github-copilot-app/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://github.blog/changelog/2026-09-30-hydrafusion-in-vs-code-and-the-github-copilot-app/"},"snippet":null,"score":null},{"slug":"gemini-4-argon-our-next-era-of-frontier-intelligence","title":"Gemini 4 Argon: our next era of frontier intelligence","subtitle":null,"summary":"Today, we’re announcing our new frontier model, Gemini 4 Argon, which is rolling out to a set of trusted cyber defenders through our Fairwind Program. Built to sustain deep reasoning across complex, longhorizon workflows, Argon is fundamentally changing the way we work and build at Google.","content_type":"announcement","language":"en","canonical_url":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-4-argon/","author":{"name":"Koray Kavukcuoglu","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Google","url":"https://blog.google/","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Google","slug":"google","url":"https://listedarticles.com/topics/google"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"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":1378,"reading_minutes":6,"published_at":"2026-09-30T00:00:00.000Z","added_at":"2026-09-30T21:16:47.028Z","updated_at":"2026-09-30T21:16:47.028Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/gemini-4-argon-our-next-era-of-frontier-intelligence","markdown_url":"https://listedarticles.com/articles/gemini-4-argon-our-next-era-of-frontier-intelligence.md","example":false,"citation":"Koray Kavukcuoglu, Google. \"Gemini 4 Argon: our next era of frontier intelligence.\" 30 Sept 2026. https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-4-argon/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-4-argon/"},"snippet":null,"score":null},{"slug":"comparing-muon-normuon-and-adamw-for-fine-tuning-a-dense-retriever","title":"Comparing Muon, NorMuon and AdamW for Fine-tuning a Dense Retriever","subtitle":null,"summary":"Qingcheng Zeng gives Muon and NorMuon the same tuning budget as AdamW when fine-tuning a contrastively pretrained dense retriever: lower training loss, no BEIR win. Learning rate and transfer matter more than the optimizer.","content_type":"research","language":"en","canonical_url":"https://qcznlp.github.io/blog/2026/muon-vs-adamw/","author":{"name":"Qingcheng Zeng","url":"https://qcznlp.github.io/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Qingcheng Zeng","url":"https://qcznlp.github.io/","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":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"Programming","slug":"programming","url":"https://listedarticles.com/topics/programming"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1151,"reading_minutes":5,"published_at":"2026-09-30T00:00:00.000Z","added_at":"2026-09-30T06:13:44.584Z","updated_at":"2026-09-30T06:13:44.584Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/comparing-muon-normuon-and-adamw-for-fine-tuning-a-dense-retriever","markdown_url":"https://listedarticles.com/articles/comparing-muon-normuon-and-adamw-for-fine-tuning-a-dense-retriever.md","example":false,"citation":"Qingcheng Zeng, Qingcheng Zeng. \"Comparing Muon, NorMuon and AdamW for Fine-tuning a Dense Retriever.\" 30 Sept 2026. https://qcznlp.github.io/blog/2026/muon-vs-adamw/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://qcznlp.github.io/blog/2026/muon-vs-adamw/"},"snippet":null,"score":null},{"slug":"language-models-for-text-classification-from-bag-of-words-to-jev","title":"Language Models for Text Classification: From Bag-of-Words to Jev","subtitle":"A visual guide to bag-of-words, RNNs, CNNs, transformers, Jev-like APIs, and calibration","summary":"Sebastian Raschka walks from classic bag-of-words classifiers through RNNs, CNNs, and transformers to TypeSafe AI's Jev—explaining APIs, IMDb benchmarks, calibration, and why decision models matter for agent harnesses.","content_type":"essay","language":"en","canonical_url":"https://magazine.sebastianraschka.com/p/classifier-history-and-jev","author":{"name":"Sebastian Raschka","url":"https://sebastianraschka.com/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Sebastian Raschka","url":"https://magazine.sebastianraschka.com/","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":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"}],"about_listings":[{"slug":"typesafe-ai","name":"TypeSafe AI","listing_type":"company","url":"https://listedstartups.com/companies/typesafe-ai"},{"slug":"jev","name":"Jev","listing_type":"product","url":"https://listedstartups.com/products/jev"}],"cover_image_url":null,"license":"all-rights-reserved","word_count":1076,"reading_minutes":5,"published_at":"2026-09-29T12:00:00.000Z","added_at":"2026-09-30T03:18:45.658Z","updated_at":"2026-09-30T03:18:45.658Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/language-models-for-text-classification-from-bag-of-words-to-jev","markdown_url":"https://listedarticles.com/articles/language-models-for-text-classification-from-bag-of-words-to-jev.md","example":false,"citation":"Sebastian Raschka, Sebastian Raschka. \"Language Models for Text Classification: From Bag-of-Words to Jev.\" 29 Sept 2026. https://magazine.sebastianraschka.com/p/classifier-history-and-jev (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://magazine.sebastianraschka.com/p/classifier-history-and-jev"},"snippet":null,"score":null},{"slug":"context-language-models","title":"Context Language Models","subtitle":null,"summary":"CLMs treat context as an editable file so models natively manage their own context—beating harness baselines on BrowseComp-Plus and long-horizon coding with fewer FLOPs, plus in-context skill evolution and RL for context management.","content_type":"research","language":"en","canonical_url":"https://arxiv.org/abs/2609.37725","author":{"name":"Rulin Shao et al.","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":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"},{"name":"Performance","slug":"performance","url":"https://listedarticles.com/topics/performance"}],"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":699,"reading_minutes":3,"published_at":"2026-09-29T00:00:00.000Z","added_at":"2026-10-02T03:18:41.475Z","updated_at":"2026-10-02T03:18:41.475Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/context-language-models","markdown_url":"https://listedarticles.com/articles/context-language-models.md","example":false,"citation":"Rulin Shao et al., arXiv. \"Context Language Models.\" 29 Sept 2026. https://arxiv.org/abs/2609.37725 (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://arxiv.org/abs/2609.37725"},"snippet":null,"score":null},{"slug":"how-to-build-a-reliable-ai-assistant-with-the-claude-api","title":"How to Build a Reliable AI Assistant with the Claude API","subtitle":null,"summary":"A freeCodeCamp tutorial building ShopHelper with the Claude API: conversation history, tools, multi-block responses, workflow patterns, and evaluating whether prompt changes actually help.","content_type":"tutorial","language":"en","canonical_url":"https://www.freecodecamp.org/news/how-to-build-a-reliable-ai-assistant-with-the-claude-api/","author":{"name":"Chidozie Managwu","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"freeCodeCamp","url":"https://www.freecodecamp.org","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Tutorials","slug":"tutorials","url":"https://listedarticles.com/topics/tutorials"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Programming","slug":"programming","url":"https://listedarticles.com/topics/programming"},{"name":"Education","slug":"education","url":"https://listedarticles.com/topics/education"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":2132,"reading_minutes":9,"published_at":"2026-09-29T00:00:00.000Z","added_at":"2026-09-30T12:14:06.208Z","updated_at":"2026-09-30T12:14:06.208Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/how-to-build-a-reliable-ai-assistant-with-the-claude-api","markdown_url":"https://listedarticles.com/articles/how-to-build-a-reliable-ai-assistant-with-the-claude-api.md","example":false,"citation":"Chidozie Managwu, freeCodeCamp. \"How to Build a Reliable AI Assistant with the Claude API.\" 29 Sept 2026. https://www.freecodecamp.org/news/how-to-build-a-reliable-ai-assistant-with-the-claude-api/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.freecodecamp.org/news/how-to-build-a-reliable-ai-assistant-with-the-claude-api/"},"snippet":null,"score":null},{"slug":"openai-connects-the-dots","title":"OpenAI connects the Dots","subtitle":null,"summary":"Casey Newton’s hands-on take on OpenAI’s Dots agents at DevDay: capable coworking inside ChatGPT, paid-only positioning versus Meta Muse, and the trust/safety tradeoffs of always-on agents.","content_type":"opinion","language":"en","canonical_url":"https://www.platformer.news/openai-dots-agents-devday-2026/","author":{"name":"Casey Newton","url":"https://www.platformer.news/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Platformer","url":"https://www.platformer.news/","listing_slug":null,"listing":null},"topics":[{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"},{"name":"Opinion","slug":"opinion","url":"https://listedarticles.com/topics/opinion"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Productivity","slug":"productivity","url":"https://listedarticles.com/topics/productivity"},{"name":"AI Safety","slug":"ai-safety","url":"https://listedarticles.com/topics/ai-safety"}],"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":2024,"reading_minutes":9,"published_at":"2026-09-29T00:00:00.000Z","added_at":"2026-09-30T09:12:55.919Z","updated_at":"2026-09-30T09:12:55.919Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/openai-connects-the-dots","markdown_url":"https://listedarticles.com/articles/openai-connects-the-dots.md","example":false,"citation":"Casey Newton, Platformer. \"OpenAI connects the Dots.\" 29 Sept 2026. https://www.platformer.news/openai-dots-agents-devday-2026/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.platformer.news/openai-dots-agents-devday-2026/"},"snippet":null,"score":null},{"slug":"introducing-the-agents-api","title":"Introducing the Agents API","subtitle":null,"summary":"OpenAI launches the Agents API in public beta: a managed Codex harness with durable cloud sessions, sandbox compute, context compaction, subagents, and resumable multi-hour agent work for developers.","content_type":"announcement","language":"en","canonical_url":"https://openai.com/index/introducing-the-agents-api/","author":{"name":"OpenAI","url":"https://openai.com/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"OpenAI","url":"https://openai.com/","listing_slug":null,"listing":null},"topics":[{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"},{"name":"Developer Tools","slug":"developer-tools","url":"https://listedarticles.com/topics/developer-tools"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Infrastructure","slug":"infrastructure","url":"https://listedarticles.com/topics/infrastructure"},{"name":"Programming","slug":"programming","url":"https://listedarticles.com/topics/programming"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1539,"reading_minutes":7,"published_at":"2026-09-29T00:00:00.000Z","added_at":"2026-09-30T06:14:08.672Z","updated_at":"2026-09-30T06:14:08.672Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/introducing-the-agents-api","markdown_url":"https://listedarticles.com/articles/introducing-the-agents-api.md","example":false,"citation":"OpenAI, OpenAI. \"Introducing the Agents API.\" 29 Sept 2026. https://openai.com/index/introducing-the-agents-api/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://openai.com/index/introducing-the-agents-api/"},"snippet":null,"score":null},{"slug":"introducing-claude-sonnet-5-5","title":"Introducing Claude Sonnet 5.5","subtitle":null,"summary":"Anthropic introduces Claude Sonnet 5.5, a faster and lower-cost complement to Opus 5.5 that improves agentic coding and everyday task performance versus Sonnet 5.","content_type":"announcement","language":"en","canonical_url":"https://www.anthropic.com/claude-sonnet-5-5","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":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Announcements","slug":"announcements","url":"https://listedarticles.com/topics/announcements"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"}],"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":1747,"reading_minutes":8,"published_at":"2026-09-28T16:00:00.000Z","added_at":"2026-09-28T18:15:15.692Z","updated_at":"2026-09-28T18:15:15.692Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/introducing-claude-sonnet-5-5","markdown_url":"https://listedarticles.com/articles/introducing-claude-sonnet-5-5.md","example":false,"citation":"Anthropic, Anthropic. \"Introducing Claude Sonnet 5.5.\" 28 Sept 2026. https://www.anthropic.com/claude-sonnet-5-5 (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.anthropic.com/claude-sonnet-5-5"},"snippet":null,"score":null},{"slug":"build-an-llm-tokenizer-and-attention-from-scratch-in-typescript","title":"Build an LLM Tokenizer and Attention from Scratch in TypeScript","subtitle":null,"summary":"SitePoint tutorial that implements BPE tokenization, cosine similarity vector search, and scaled dot-product attention in TypeScript—exposing LLM primitives as ordinary readable code.","content_type":"tutorial","language":"en","canonical_url":"https://www.sitepoint.com/building-llm-primitives-from-scratch-typescript/","author":{"name":"SitePoint Team","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"SitePoint","url":"https://www.sitepoint.com","listing_slug":null,"listing":null},"topics":[{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Tutorials","slug":"tutorials","url":"https://listedarticles.com/topics/tutorials"},{"name":"Programming","slug":"programming","url":"https://listedarticles.com/topics/programming"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"},{"name":"Education","slug":"education","url":"https://listedarticles.com/topics/education"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":5827,"reading_minutes":25,"published_at":"2026-09-28T14:42:29.000Z","added_at":"2026-09-30T12:14:09.501Z","updated_at":"2026-09-30T12:14:09.501Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/build-an-llm-tokenizer-and-attention-from-scratch-in-typescript","markdown_url":"https://listedarticles.com/articles/build-an-llm-tokenizer-and-attention-from-scratch-in-typescript.md","example":false,"citation":"SitePoint Team, SitePoint. \"Build an LLM Tokenizer and Attention from Scratch in TypeScript.\" 28 Sept 2026. https://www.sitepoint.com/building-llm-primitives-from-scratch-typescript/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.sitepoint.com/building-llm-primitives-from-scratch-typescript/"},"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}],"total":194,"count":20,"next_offset":20,"has_more":true,"query":{"q":null,"content_type":null,"topic":"llms","publisher":null,"about":null,"author":null,"language":null,"sort":"newest","limit":20,"offset":0}}