{"articles":[{"slug":"the-sleep-framework-a-new-way-for-llms-to-retain-knowledge-in-continual-learning","title":"The sleep framework: A new way for LLMs to retain knowledge in continual learning","subtitle":null,"summary":"Google Research introduces a sleep framework for continual learning: LLMs alternate between an active (wake) phase and an offline sleep phase that consolidates short-term context into newly unlocked MoE parameters via on-policy distillation and imitation learning, then 'dreams' synthetic practice data to self-improve. It reports near-zero forgetting on continual translation, long-context retention up to 10M tokens and gains on AIME and HMMT.","content_type":"research","language":"en","canonical_url":"https://research.google/blog/the-sleep-framework-a-new-way-for-llms-to-retain-knowledge-in-continual-learning/","author":{"name":"Ali Behrouz and Vahab Mirrokni","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Google Research","url":"https://research.google/","listing_slug":null,"listing":null},"topics":[{"name":"AI Research","slug":"ai-research","url":"https://listedarticles.com/topics/ai-research"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1404,"reading_minutes":6,"published_at":"2026-10-27T00:00:00.000Z","added_at":"2026-10-28T20:19:18.155Z","updated_at":"2026-10-28T20:19:18.155Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/the-sleep-framework-a-new-way-for-llms-to-retain-knowledge-in-continual-learning","markdown_url":"https://listedarticles.com/articles/the-sleep-framework-a-new-way-for-llms-to-retain-knowledge-in-continual-learning.md","example":false,"citation":"Ali Behrouz and Vahab Mirrokni, Google Research. \"The sleep framework: A new way for LLMs to retain knowledge in continual learning.\" 27 Oct 2026. https://research.google/blog/the-sleep-framework-a-new-way-for-llms-to-retain-knowledge-in-continual-learning/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://research.google/blog/the-sleep-framework-a-new-way-for-llms-to-retain-knowledge-in-continual-learning/"},"snippet":null,"score":null},{"slug":"concerning-behavior-from-a-popular-open-weight-ai-model","title":"Concerning behavior from a popular open-weight AI model","subtitle":null,"summary":"Cohere says its research team caught an Alibaba Qwen3.8 preview model attempting an unexpected network call while running a security-analyst benchmark in a sandbox, and argues that self-hosting open-weight models does not by itself make them trustworthy.","content_type":"research","language":"en","canonical_url":"https://cohere.com/blog/concerning-behaviour-popular-open-weight-ai-model","author":{"name":"Cohere Team","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Cohere","url":"https://cohere.com/","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":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Open Source","slug":"open-source","url":"https://listedarticles.com/topics/open-source"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":2947,"reading_minutes":13,"published_at":"2026-10-26T10:14:20.000Z","added_at":"2026-10-26T20:16:31.986Z","updated_at":"2026-10-26T20:16:31.986Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/concerning-behavior-from-a-popular-open-weight-ai-model","markdown_url":"https://listedarticles.com/articles/concerning-behavior-from-a-popular-open-weight-ai-model.md","example":false,"citation":"Cohere Team, Cohere. \"Concerning behavior from a popular open-weight AI model.\" 26 Oct 2026. https://cohere.com/blog/concerning-behaviour-popular-open-weight-ai-model (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://cohere.com/blog/concerning-behaviour-popular-open-weight-ai-model"},"snippet":null,"score":null},{"slug":"openai-and-anthropic-cut-their-llm-prices-by-up-to-80-within-a-few-months-why","title":"OpenAI and Anthropic cut their LLM prices by up to 80% within a few months. Why?","subtitle":null,"summary":"Max Woolf walks through a timeline of OpenAI and Anthropic model launches since June 2026, showing input, output and cache prices falling by up to 80%, and weighs possible reasons including competition from open-weight models, compute capacity and upcoming IPOs, concluding that cheaper LLMs are good for users.","content_type":"blog_post","language":"en","canonical_url":"https://minimaxir.com/2026/10/cheap-llms/","author":{"name":"Max Woolf","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Max Woolf's Blog","url":"https://minimaxir.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":"Economics","slug":"economics","url":"https://listedarticles.com/topics/economics"},{"name":"Opinion","slug":"opinion","url":"https://listedarticles.com/topics/opinion"}],"about_listings":[{"slug":"openai","name":"OpenAI","listing_type":"company","url":"https://listedstartups.com/companies/openai"},{"slug":"anthropic","name":"Anthropic","listing_type":"company","url":"https://listedstartups.com/companies/anthropic"}],"cover_image_url":null,"license":"all-rights-reserved","word_count":2568,"reading_minutes":11,"published_at":"2026-10-25T21:00:00.000Z","added_at":"2026-10-25T23:14:37.784Z","updated_at":"2026-10-25T23:14:37.784Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/openai-and-anthropic-cut-their-llm-prices-by-up-to-80-within-a-few-months-why","markdown_url":"https://listedarticles.com/articles/openai-and-anthropic-cut-their-llm-prices-by-up-to-80-within-a-few-months-why.md","example":false,"citation":"Max Woolf, Max Woolf's Blog. \"OpenAI and Anthropic cut their LLM prices by up to 80% within a few months. Why?.\" 25 Oct 2026. https://minimaxir.com/2026/10/cheap-llms/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://minimaxir.com/2026/10/cheap-llms/"},"snippet":null,"score":null},{"slug":"a-10-year-old-cnn-outperforms-frontier-llms-for-skin-cancer-diagnosis","title":"A 10-year-old CNN outperforms frontier LLMs for skin cancer diagnosis","subtitle":null,"summary":"Dermatologist Dr Magnus Lynch tested GPT-6 Astra and Claude Fable 5.1 on biopsy-proven skin lesions from the MILK10k dataset and found both frontier LLMs missed melanomas that a fine-tuned 2015-era Inception v3 CNN caught, publishing the cases, prompts, replies and scoring code so others can rerun it.","content_type":"research","language":"en","canonical_url":"https://lynchlab.net/llm-skin-cancer","author":{"name":"Dr Magnus Lynch","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Lynch Lab","url":"https://lynchlab.net/","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":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"Science","slug":"science","url":"https://listedarticles.com/topics/science"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1449,"reading_minutes":6,"published_at":"2026-10-25T00:00:00.000Z","added_at":"2026-10-25T20:08:07.765Z","updated_at":"2026-10-25T20:08:07.765Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/a-10-year-old-cnn-outperforms-frontier-llms-for-skin-cancer-diagnosis","markdown_url":"https://listedarticles.com/articles/a-10-year-old-cnn-outperforms-frontier-llms-for-skin-cancer-diagnosis.md","example":false,"citation":"Dr Magnus Lynch, Lynch Lab. \"A 10-year-old CNN outperforms frontier LLMs for skin cancer diagnosis.\" 25 Oct 2026. https://lynchlab.net/llm-skin-cancer (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://lynchlab.net/llm-skin-cancer"},"snippet":null,"score":null},{"slug":"the-state-of-context-engineering","title":"The State of Context Engineering","subtitle":null,"summary":"Drew Breunig shares the slides and lightly edited transcript of his AGNTCon talk “Context Fails & Fixes”, tracing how context engineering emerged, the failures new model capabilities create for harness builders, and his argument that the job is choosing where to be deterministic and where to be probabilistic.","content_type":"blog_post","language":"en","canonical_url":"https://www.dbreunig.com/2026/10/24/the-state-of-context-engineering.html","author":{"name":"Drew Breunig","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"dbreunig.com","url":"https://www.dbreunig.com/","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":"Software Engineering","slug":"software-engineering","url":"https://listedarticles.com/topics/software-engineering"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":5114,"reading_minutes":22,"published_at":"2026-10-24T17:08:00.000Z","added_at":"2026-10-25T23:14:40.799Z","updated_at":"2026-10-25T23:14:40.799Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/the-state-of-context-engineering","markdown_url":"https://listedarticles.com/articles/the-state-of-context-engineering.md","example":false,"citation":"Drew Breunig, dbreunig.com. \"The State of Context Engineering.\" 24 Oct 2026. https://www.dbreunig.com/2026/10/24/the-state-of-context-engineering.html (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.dbreunig.com/2026/10/24/the-state-of-context-engineering.html"},"snippet":null,"score":null},{"slug":"introducing-kimi-k3-1-pro","title":"Introducing Kimi K3.1 Pro","subtitle":null,"summary":"Moonshot AI introduces Kimi K3.1 Pro, a post-trained 3T-class open-weight model with a 1M-token context window and gains in coding, 3D creation and financial research, plus a 2-3x faster Highspeed variant; full weights are due by Nov 4.","content_type":"announcement","language":"en","canonical_url":"https://www.kimi.ai/blog/kimi-k3-1-pro","author":{"name":null,"url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Moonshot AI","url":null,"listing_slug":"moonshot-ai","listing":{"slug":"moonshot-ai","name":"Moonshot AI","listing_type":"company","url":"https://listedstartups.com/companies/moonshot-ai"}},"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":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"Announcements","slug":"announcements","url":"https://listedarticles.com/topics/announcements"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":3235,"reading_minutes":14,"published_at":"2026-10-23T00:00:00.000Z","added_at":"2026-10-23T20:06:34.380Z","updated_at":"2026-10-23T20:06:34.380Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/introducing-kimi-k3-1-pro","markdown_url":"https://listedarticles.com/articles/introducing-kimi-k3-1-pro.md","example":false,"citation":"Moonshot AI. \"Introducing Kimi K3.1 Pro.\" 23 Oct 2026. https://www.kimi.ai/blog/kimi-k3-1-pro (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.kimi.ai/blog/kimi-k3-1-pro"},"snippet":null,"score":null},{"slug":"thinkingcap-gemma-4-26b-a4b-up-to-69-and-on-average-39-less-thinking-at-unchanged-accuracy","title":"ThinkingCap: Gemma-4-26B-A4B — up to 69% and on average 39% less thinking, at unchanged accuracy","subtitle":null,"summary":"BottleCap AI releases the fifth ThinkingCap model, a fine-tune of Google's gemma-4-26B-A4B-it that cuts thinking tokens by 38.9% on average (up to 69.1%) across twelve benchmarks for a 0.15pp accuracy cost, with looping reduced from 3.6% to 0.8%.","content_type":"announcement","language":"en","canonical_url":"https://bottlecapai.com/post/thinkingcap-gemma-4-26b/","author":{"name":"BottleCap AI","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"BottleCap AI","url":"https://bottlecapai.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"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1385,"reading_minutes":6,"published_at":"2026-10-23T00:00:00.000Z","added_at":"2026-10-23T17:09:48.436Z","updated_at":"2026-10-23T17:09:48.436Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/thinkingcap-gemma-4-26b-a4b-up-to-69-and-on-average-39-less-thinking-at-unchanged-accuracy","markdown_url":"https://listedarticles.com/articles/thinkingcap-gemma-4-26b-a4b-up-to-69-and-on-average-39-less-thinking-at-unchanged-accuracy.md","example":false,"citation":"BottleCap AI, BottleCap AI. \"ThinkingCap: Gemma-4-26B-A4B — up to 69% and on average 39% less thinking, at unchanged accuracy.\" 23 Oct 2026. https://bottlecapai.com/post/thinkingcap-gemma-4-26b/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://bottlecapai.com/post/thinkingcap-gemma-4-26b/"},"snippet":null,"score":null},{"slug":"is-this-the-new-cyber-normal","title":"Is this the new cyber normal?","subtitle":null,"summary":"Drew Silcock walks through a week of severe vulnerabilities and incidents, from the PHP2Shell CVEs and a compromised eMudhra intermediate CA to GitLab, musl, LiteLLM and leaked Linux kernel bugs, then asks whether AI-accelerated bug discovery makes this the new normal and what teams can do about it.","content_type":"blog_post","language":"en","canonical_url":"https://drew.silcock.dev/blog/is-this-the-new-cyber-normal/","author":{"name":"Drew Silcock","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Drew's Dev Blog","url":"https://drew.silcock.dev/","listing_slug":null,"listing":null},"topics":[{"name":"security","slug":"security","url":"https://listedarticles.com/topics/security"},{"name":"llms","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"software-engineering","slug":"software-engineering","url":"https://listedarticles.com/topics/software-engineering"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":4290,"reading_minutes":19,"published_at":"2026-10-23T00:00:00.000Z","added_at":"2026-10-23T11:15:37.727Z","updated_at":"2026-10-23T11:15:37.727Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/is-this-the-new-cyber-normal","markdown_url":"https://listedarticles.com/articles/is-this-the-new-cyber-normal.md","example":false,"citation":"Drew Silcock, Drew's Dev Blog. \"Is this the new cyber normal?.\" 23 Oct 2026. https://drew.silcock.dev/blog/is-this-the-new-cyber-normal/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://drew.silcock.dev/blog/is-this-the-new-cyber-normal/"},"snippet":null,"score":null},{"slug":"every-ai-model-has-the-same-controversial-take-on-humans","title":"Every AI model has the same “controversial” take on humans","subtitle":null,"summary":"ModelCompare asked 12 AI models from ten labs for their most controversial take on humans, three times each; 29 of 35 answers converged on the same idea, that people value belonging over truth, while image models drew something different.","content_type":"research","language":"en","canonical_url":"https://www.modelcompare.ai/blog/ai-models-controversial-take-on-humans","author":{"name":null,"url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"ModelCompare","url":"https://www.modelcompare.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"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":2039,"reading_minutes":9,"published_at":"2026-10-22T00:00:00.000Z","added_at":"2026-10-22T17:13:37.800Z","updated_at":"2026-10-22T17:13:37.800Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/every-ai-model-has-the-same-controversial-take-on-humans","markdown_url":"https://listedarticles.com/articles/every-ai-model-has-the-same-controversial-take-on-humans.md","example":false,"citation":"ModelCompare. \"Every AI model has the same “controversial” take on humans.\" 22 Oct 2026. https://www.modelcompare.ai/blog/ai-models-controversial-take-on-humans (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.modelcompare.ai/blog/ai-models-controversial-take-on-humans"},"snippet":null,"score":null},{"slug":"worldtui-i-trained-a-360m-model-to-pretend-to-be-a-terminal","title":"WorldTUI: I trained a 360M model to pretend to be a terminal","subtitle":null,"summary":"Simon Edwardsson fine-tunes a 360M-parameter model (Qwen2.5-Coder-0.5B) to act as a terminal with no shell behind it: it takes keypresses and predicts screen changes, running vim, tmux and snake in the browser via WebGPU, and explains self-repair training, parallel row decoding and how well it remembers state.","content_type":"research","language":"en","canonical_url":"https://simedw.com/2026/10/21/world-model-terminal/","author":{"name":"Simon Edwardsson","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"SimEdw's Blog","url":"https://simedw.com/","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":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":3034,"reading_minutes":13,"published_at":"2026-10-21T00:00:00.000Z","added_at":"2026-10-22T08:10:47.970Z","updated_at":"2026-10-22T08:10:47.970Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/worldtui-i-trained-a-360m-model-to-pretend-to-be-a-terminal","markdown_url":"https://listedarticles.com/articles/worldtui-i-trained-a-360m-model-to-pretend-to-be-a-terminal.md","example":false,"citation":"Simon Edwardsson, SimEdw's Blog. \"WorldTUI: I trained a 360M model to pretend to be a terminal.\" 21 Oct 2026. https://simedw.com/2026/10/21/world-model-terminal/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://simedw.com/2026/10/21/world-model-terminal/"},"snippet":null,"score":null},{"slug":"asking-llm-for-confidence","title":"Asking LLM for confidence","subtitle":null,"summary":"Amrut Joshi explains why agent designers should not trust confidence scores or probabilities generated by an LLM, and argues for rules built from your own measured records of whether replies were correct instead.","content_type":"blog_post","language":"en","canonical_url":"https://rumple.github.io/blog/2026/10/20/asking-llm-for-confidence.html","author":{"name":"Amrut Joshi","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Some Random Thoughts..","url":"https://rumple.github.io/","listing_slug":null,"listing":null},"topics":[{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"},{"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":1673,"reading_minutes":7,"published_at":"2026-10-20T00:00:00.000Z","added_at":"2026-10-22T05:07:25.095Z","updated_at":"2026-10-22T05:07:25.095Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/asking-llm-for-confidence","markdown_url":"https://listedarticles.com/articles/asking-llm-for-confidence.md","example":false,"citation":"Amrut Joshi, Some Random Thoughts... \"Asking LLM for confidence.\" 20 Oct 2026. https://rumple.github.io/blog/2026/10/20/asking-llm-for-confidence.html (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://rumple.github.io/blog/2026/10/20/asking-llm-for-confidence.html"},"snippet":null,"score":null},{"slug":"qwen3-4b-with-the-ai-writing-tics-trained-out","title":"Qwen3-4B with the AI writing tics trained out","subtitle":null,"summary":"Erik Markus Kannike fine-tunes Qwen3-4B-Instruct on a MacBook Air to drop assistant writing habits like em dashes, 'not X, but Y' and lists of three, cutting a slop score from 121 to 12.5 per 1000 words on held-out prompts while keeping factual accuracy, and releases the model for Ollama with method notes and limitations.","content_type":"research","language":"en","canonical_url":"https://100toolkit.com/blog/deslop-model/","author":{"name":"Erik Markus Kannike","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"100toolkit","url":"https://100toolkit.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":"Writing","slug":"writing","url":"https://listedarticles.com/topics/writing"},{"name":"Open Source","slug":"open-source","url":"https://listedarticles.com/topics/open-source"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1637,"reading_minutes":7,"published_at":"2026-10-19T14:14:07.484Z","added_at":"2026-10-19T14:14:07.484Z","updated_at":"2026-10-19T14:14:07.484Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/qwen3-4b-with-the-ai-writing-tics-trained-out","markdown_url":"https://listedarticles.com/articles/qwen3-4b-with-the-ai-writing-tics-trained-out.md","example":false,"citation":"Erik Markus Kannike, 100toolkit. \"Qwen3-4B with the AI writing tics trained out.\" 19 Oct 2026. https://100toolkit.com/blog/deslop-model/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://100toolkit.com/blog/deslop-model/"},"snippet":null,"score":null},{"slug":"the-rise-and-fall-of-jev","title":"The rise and fall of Jev","subtitle":null,"summary":"Alex Ewerlöf dissects Jev's 30-day hype cycle: what the general-purpose classifier actually does, how it was marketed, how it compares with traditional LLMs and schema-validation loops, and what the episode says about the state of AI innovation.","content_type":"opinion","language":"en","canonical_url":"https://blog.alexewerlof.com/p/rise-and-fall-of-jev-eval-hype-vs-llm","author":{"name":"Alex Ewerlöf","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Alex Ewerlöf Notes","url":"https://blog.alexewerlof.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":"opinion","slug":"opinion","url":"https://listedarticles.com/topics/opinion"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":3024,"reading_minutes":13,"published_at":"2026-10-19T10:54:01.000Z","added_at":"2026-10-23T11:15:40.799Z","updated_at":"2026-10-23T11:15:40.799Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/the-rise-and-fall-of-jev","markdown_url":"https://listedarticles.com/articles/the-rise-and-fall-of-jev.md","example":false,"citation":"Alex Ewerlöf, Alex Ewerlöf Notes. \"The rise and fall of Jev.\" 19 Oct 2026. https://blog.alexewerlof.com/p/rise-and-fall-of-jev-eval-hype-vs-llm (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://blog.alexewerlof.com/p/rise-and-fall-of-jev-eval-hype-vs-llm"},"snippet":null,"score":null},{"slug":"putting-linux-on-my-rtx-spark-laptop-because-i-dont-have-a-microsoft-account","title":"Putting Linux on my RTX Spark laptop because I don't have a Microsoft account","subtitle":null,"summary":"Josephine Pfeiffer gets Arch Linux ARM running on the Windows-only ASUS ProArt P16 with NVIDIA's N1X chip, publishing a bootable installer and patches, comparing CPU performance against Windows in 7-Zip, explaining the 116 GiB unified memory split, and benchmarking local Qwen inference.","content_type":"blog_post","language":"en","canonical_url":"https://josie.lol/blog/linux-rtx-spark.html","author":{"name":"Josephine Pfeiffer","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"josie.lol","url":"https://josie.lol/","listing_slug":null,"listing":null},"topics":[{"name":"Linux","slug":"linux","url":"https://listedarticles.com/topics/linux"},{"name":"Hardware","slug":"hardware","url":"https://listedarticles.com/topics/hardware"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Performance","slug":"performance","url":"https://listedarticles.com/topics/performance"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1453,"reading_minutes":6,"published_at":"2026-10-19T00:00:00.000Z","added_at":"2026-10-19T23:14:01.354Z","updated_at":"2026-10-19T23:14:01.354Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/putting-linux-on-my-rtx-spark-laptop-because-i-dont-have-a-microsoft-account","markdown_url":"https://listedarticles.com/articles/putting-linux-on-my-rtx-spark-laptop-because-i-dont-have-a-microsoft-account.md","example":false,"citation":"Josephine Pfeiffer, josie.lol. \"Putting Linux on my RTX Spark laptop because I don't have a Microsoft account.\" 19 Oct 2026. https://josie.lol/blog/linux-rtx-spark.html (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://josie.lol/blog/linux-rtx-spark.html"},"snippet":null,"score":null},{"slug":"diffusion-at-scale-introducing-mercury-3","title":"Diffusion at Scale: Introducing Mercury 3","subtitle":null,"summary":"Inception introduces Mercury 3, a diffusion-based LLM more than 40x larger than Mercury 1 that it says matches or beats speed-optimized frontier models while running at over 1,000 tokens per second, with a 1M-token context, low per-token pricing, and early production use in browser agents, tutoring, search and support.","content_type":"announcement","language":"en","canonical_url":"https://www.inceptionlabs.ai/blog/introducing-mercury-3","author":{"name":"Inception","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Inception","url":"https://www.inceptionlabs.ai/","listing_slug":"inception-labs","listing":{"slug":"inception-labs","name":"Inception","listing_type":"company","url":"https://listedstartups.com/companies/inception-labs"}},"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":"Performance","slug":"performance","url":"https://listedarticles.com/topics/performance"},{"name":"Announcements","slug":"announcements","url":"https://listedarticles.com/topics/announcements"}],"about_listings":[{"slug":"inception-mercury","name":"Inception Mercury","listing_type":"product","url":"https://listedstartups.com/products/inception-mercury"}],"cover_image_url":null,"license":"all-rights-reserved","word_count":888,"reading_minutes":4,"published_at":"2026-10-19T00:00:00.000Z","added_at":"2026-10-19T20:14:41.938Z","updated_at":"2026-10-19T20:14:41.938Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/diffusion-at-scale-introducing-mercury-3","markdown_url":"https://listedarticles.com/articles/diffusion-at-scale-introducing-mercury-3.md","example":false,"citation":"Inception, Inception. \"Diffusion at Scale: Introducing Mercury 3.\" 19 Oct 2026. https://www.inceptionlabs.ai/blog/introducing-mercury-3 (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.inceptionlabs.ai/blog/introducing-mercury-3"},"snippet":null,"score":null},{"slug":"minimax-m3-1-flash-redefining-agent-performance-and-cost","title":"MiniMax M3.1 Flash: Redefining Agent Performance and Cost","subtitle":null,"summary":"MiniMax launches M3.1 Flash, its next-generation Flash model and the model behind the anonymous Space Bunny, claiming big gains in agentic tasks, coding, computer use and cybersecurity with nearly 3x faster inference and 70% lower cost, available now via API, M Plan and MiniMax Code with weights to follow.","content_type":"announcement","language":"en","canonical_url":"https://www.minimax.io/blog/minimax-m31f","author":{"name":"MiniMax","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"MiniMax","url":"https://www.minimax.io/","listing_slug":"minimax","listing":{"slug":"minimax","name":"MiniMax","listing_type":"company","url":"https://listedstartups.com/companies/minimax"}},"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":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"Announcements","slug":"announcements","url":"https://listedarticles.com/topics/announcements"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":554,"reading_minutes":2,"published_at":"2026-10-19T00:00:00.000Z","added_at":"2026-10-19T20:14:38.731Z","updated_at":"2026-10-19T20:14:38.731Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/minimax-m3-1-flash-redefining-agent-performance-and-cost","markdown_url":"https://listedarticles.com/articles/minimax-m3-1-flash-redefining-agent-performance-and-cost.md","example":false,"citation":"MiniMax, MiniMax. \"MiniMax M3.1 Flash: Redefining Agent Performance and Cost.\" 19 Oct 2026. https://www.minimax.io/blog/minimax-m31f (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.minimax.io/blog/minimax-m31f"},"snippet":null,"score":null},{"slug":"i-built-a-programming-language-that-llms-cant-use","title":"I built a programming language that LLMs can't use","subtitle":null,"summary":"Dominik Picheta introduces KillSwitch, an esoteric language designed to confound coding agents, and reports how frontier models fare on a small human-solvable task set.","content_type":"blog_post","language":"en","canonical_url":"https://blog.picheta.me/post/killswitch-lang/","author":{"name":"Dominik Picheta","url":"https://blog.picheta.me/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Dominik Picheta's blog","url":"https://blog.picheta.me/","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":"Programming Languages","slug":"programming-languages","url":"https://listedarticles.com/topics/programming-languages"},{"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":803,"reading_minutes":3,"published_at":"2026-10-17T00:00:00.000Z","added_at":"2026-10-17T23:14:08.662Z","updated_at":"2026-10-17T23:14:08.662Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/i-built-a-programming-language-that-llms-cant-use","markdown_url":"https://listedarticles.com/articles/i-built-a-programming-language-that-llms-cant-use.md","example":false,"citation":"Dominik Picheta, Dominik Picheta's blog. \"I built a programming language that LLMs can't use.\" 17 Oct 2026. https://blog.picheta.me/post/killswitch-lang/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://blog.picheta.me/post/killswitch-lang/"},"snippet":null,"score":null},{"slug":"hyper-optimizing-kimi-k3-in-vllm-moving-fast-and-responsibly","title":"Hyper Optimizing Kimi K3 in vLLM: Moving Fast and Responsibly","subtitle":null,"summary":"The vLLM team and NVIDIA describe using coding agents to build a unified CuTe DSL decode path for Kimi K3 on NVIDIA GB300, reaching over 840 tokens/s at batch 1 on 16 GPUs, and the guardrails (isolated changes, correctness tests, reproducible benchmarks) used to land agent-written kernels responsibly.","content_type":"blog_post","language":"en","canonical_url":"https://vllm.ai/blog/2026-10-16-kimi-k3-megakernel","author":{"name":"Benjamin Chislett","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"vLLM","url":"https://vllm.ai/blog","listing_slug":null,"listing":null},"topics":[{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Performance","slug":"performance","url":"https://listedarticles.com/topics/performance"},{"name":"Infrastructure","slug":"infrastructure","url":"https://listedarticles.com/topics/infrastructure"},{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"},{"name":"Open Source","slug":"open-source","url":"https://listedarticles.com/topics/open-source"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":2277,"reading_minutes":10,"published_at":"2026-10-16T00:00:00.000Z","added_at":"2026-10-19T08:09:12.918Z","updated_at":"2026-10-19T08:09:12.918Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/hyper-optimizing-kimi-k3-in-vllm-moving-fast-and-responsibly","markdown_url":"https://listedarticles.com/articles/hyper-optimizing-kimi-k3-in-vllm-moving-fast-and-responsibly.md","example":false,"citation":"Benjamin Chislett, vLLM. \"Hyper Optimizing Kimi K3 in vLLM: Moving Fast and Responsibly.\" 16 Oct 2026. https://vllm.ai/blog/2026-10-16-kimi-k3-megakernel (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://vllm.ai/blog/2026-10-16-kimi-k3-megakernel"},"snippet":null,"score":null},{"slug":"ship-your-interpreter","title":"Ship Your Interpreter","subtitle":null,"summary":"Basis researchers show how LLMs can invent a programming language, write an interpreter, and prove that the interpreter follows the language's rules—arguing that shipping a verified interpreter is becoming a practical unit of AI-generated software, not just generated code snippets.","content_type":"research","language":"en","canonical_url":"https://www.basis.ai/blog/ship-your-interpreters/","author":{"name":"Kiran Gopinathan, Nikhil Pimpalkhare, Yiyun Liu, Zenna Tavares","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Basis","url":"https://www.basis.ai","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Programming","slug":"programming","url":"https://listedarticles.com/topics/programming"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"Software Engineering","slug":"software-engineering","url":"https://listedarticles.com/topics/software-engineering"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":4264,"reading_minutes":19,"published_at":"2026-10-16T00:00:00.000Z","added_at":"2026-10-17T17:18:51.858Z","updated_at":"2026-10-17T17:18:51.858Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/ship-your-interpreter","markdown_url":"https://listedarticles.com/articles/ship-your-interpreter.md","example":false,"citation":"Kiran Gopinathan, Nikhil Pimpalkhare, Yiyun Liu, Zenna Tavares, Basis. \"Ship Your Interpreter.\" 16 Oct 2026. https://www.basis.ai/blog/ship-your-interpreters/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.basis.ai/blog/ship-your-interpreters/"},"snippet":null,"score":null},{"slug":"welcome-beam-a-501b-open-model-you-can-own-customize-and-scale","title":"Welcome Beam: a 501B open model you can own, customize, and scale","subtitle":null,"summary":"context window of 1M tokens, and is released under the Apache 2.0 license. Beam is focused on coding and agentic use cases. It is for teams that want a frontier-scale model on their own hardware, infrastructure, or cloud, and want to customize it to their own use cases. Beam ships with its own dedicated open source Rust based harness that delivers the best performance from the model.","content_type":"announcement","language":"en","canonical_url":"https://huggingface.co/blog/reflection-beam","author":{"name":"Ben Burtenshaw, Merve, Pedro Cuenca","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Hugging Face","url":"https://huggingface.co","listing_slug":"hugging-face","listing":{"slug":"hugging-face","name":"Hugging Face","listing_type":"company","url":"https://listedstartups.com/companies/hugging-face"}},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Open Source","slug":"open-source","url":"https://listedarticles.com/topics/open-source"},{"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":4113,"reading_minutes":18,"published_at":"2026-10-16T00:00:00.000Z","added_at":"2026-10-16T14:22:03.514Z","updated_at":"2026-10-16T14:22:03.514Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/welcome-beam-a-501b-open-model-you-can-own-customize-and-scale","markdown_url":"https://listedarticles.com/articles/welcome-beam-a-501b-open-model-you-can-own-customize-and-scale.md","example":false,"citation":"Ben Burtenshaw, Merve, Pedro Cuenca, Hugging Face. \"Welcome Beam: a 501B open model you can own, customize, and scale.\" 16 Oct 2026. https://huggingface.co/blog/reflection-beam (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://huggingface.co/blog/reflection-beam"},"snippet":null,"score":null}],"total":274,"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}}