{"articles":[{"slug":"welcome-muse-spark-open-open-weight-frontier-multimodal-mixture-of-experts-model-from-meta","title":"Welcome Muse Spark Open: open-weight frontier multimodal mixture-of-experts model from Meta","subtitle":null,"summary":"Hugging Face's guide to Meta's Muse Spark Open, an 816B-parameter (42B active) open-weight multimodal mixture-of-experts model with a 1M-token context: architecture, perception and audio encoders, and how to run it with Transformers, llama.cpp, SGLang, vLLM and MLX, deploy it, fine-tune it with TRL, plus demos.","content_type":"tutorial","language":"en","canonical_url":"https://huggingface.co/blog/meta-muse-spark-open","author":{"name":"Pedro Cuenca, merve, ben burtenshaw, Guarin Flück, Quentin Gallouédec, Alvaro Bartolome, Serveurperso, Jun Kim","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":"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":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":4307,"reading_minutes":19,"published_at":"2026-10-15T00:00:00.000Z","added_at":"2026-10-18T11:12:59.238Z","updated_at":"2026-10-18T11:12:59.238Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/welcome-muse-spark-open-open-weight-frontier-multimodal-mixture-of-experts-model-from-meta","markdown_url":"https://listedarticles.com/articles/welcome-muse-spark-open-open-weight-frontier-multimodal-mixture-of-experts-model-from-meta.md","example":false,"citation":"Pedro Cuenca, merve, ben burtenshaw, Guarin Flück, Quentin Gallouédec, Alvaro Bartolome, Serveurperso, Jun Kim, Hugging Face. \"Welcome Muse Spark Open: open-weight frontier multimodal mixture-of-experts model from Meta.\" 15 Oct 2026. https://huggingface.co/blog/meta-muse-spark-open (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://huggingface.co/blog/meta-muse-spark-open"},"snippet":null,"score":null},{"slug":"how-to-be-more-ambitious-a-tutorial-for-humans-with-models","title":"How to be more ambitious: A tutorial for humans with models","subtitle":null,"summary":"Felix Rieseberg, who works on Claude at Anthropic, offers a practical tutorial for being more ambitious with AI models, grouping ambition into speed, altitude, depth and range, with worked examples around a quarterly business review and sample prompts, and closes with research on self-efficacy and why believing hard things are possible helps people achieve them.","content_type":"tutorial","language":"en","canonical_url":"https://felixrieseberg.com/how-to-be-more-ambitious-a-tutorial-for-humans-with-models/","author":{"name":"Felix Rieseberg","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Felix Rieseberg","url":"https://felixrieseberg.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":"Productivity","slug":"productivity","url":"https://listedarticles.com/topics/productivity"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":2160,"reading_minutes":9,"published_at":"2026-10-13T14:48:44.000Z","added_at":"2026-10-15T11:08:14.173Z","updated_at":"2026-10-15T11:08:14.173Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/how-to-be-more-ambitious-a-tutorial-for-humans-with-models","markdown_url":"https://listedarticles.com/articles/how-to-be-more-ambitious-a-tutorial-for-humans-with-models.md","example":false,"citation":"Felix Rieseberg, Felix Rieseberg. \"How to be more ambitious: A tutorial for humans with models.\" 13 Oct 2026. https://felixrieseberg.com/how-to-be-more-ambitious-a-tutorial-for-humans-with-models/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://felixrieseberg.com/how-to-be-more-ambitious-a-tutorial-for-humans-with-models/"},"snippet":null,"score":null},{"slug":"running-rag-with-a-small-language-model-in-the-browser","title":"Running RAG with a (small) language model in the browser","subtitle":null,"summary":"Bart de Goede extends his static blog's in-browser semantic search into full retrieval-augmented generation by running small language models client-side with transformers.js on WebGPU or WASM, and evaluates how faithful and useful answers from Qwen3, Gemma and other small models are compared with larger ones.","content_type":"tutorial","language":"en","canonical_url":"https://bart.degoe.de/rag-with-a-small-language-model-in-the-browser/","author":{"name":"Bart de Goede","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Bart de Goede","url":"https://bart.degoe.de/","listing_slug":null,"listing":null},"topics":[{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Web Development","slug":"web-development","url":"https://listedarticles.com/topics/web-development"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"},{"name":"Tutorials","slug":"tutorials","url":"https://listedarticles.com/topics/tutorials"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":2160,"reading_minutes":9,"published_at":"2026-10-12T00:00:00.000Z","added_at":"2026-10-13T17:25:10.596Z","updated_at":"2026-10-13T17:25:30.536Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/running-rag-with-a-small-language-model-in-the-browser","markdown_url":"https://listedarticles.com/articles/running-rag-with-a-small-language-model-in-the-browser.md","example":false,"citation":"Bart de Goede, Bart de Goede. \"Running RAG with a (small) language model in the browser.\" 12 Oct 2026. https://bart.degoe.de/rag-with-a-small-language-model-in-the-browser/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://bart.degoe.de/rag-with-a-small-language-model-in-the-browser/"},"snippet":null,"score":null},{"slug":"build-your-own-decision-model","title":"Build your own decision model","subtitle":null,"summary":"Nish Tahir explains \"system one\" decision models like TypeSafe AI's Jev, which answer in a single forward pass by masking the vocabulary to a fixed set of options, then walks through fine-tuning a small model on multiple-choice data and calibrating its confidence with temperature scaling, with a companion GitHub repo.","content_type":"tutorial","language":"en","canonical_url":"https://nishtahir.com/build-your-own-decision-model/","author":{"name":"Nish Tahir","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Another Dev's Two Cents","url":"https://nishtahir.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"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1019,"reading_minutes":4,"published_at":"2026-10-10T21:24:15.000Z","added_at":"2026-10-10T23:12:52.478Z","updated_at":"2026-10-10T23:12:52.478Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/build-your-own-decision-model","markdown_url":"https://listedarticles.com/articles/build-your-own-decision-model.md","example":false,"citation":"Nish Tahir, Another Dev's Two Cents. \"Build your own decision model.\" 10 Oct 2026. https://nishtahir.com/build-your-own-decision-model/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://nishtahir.com/build-your-own-decision-model/"},"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":"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":"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":"automating-eval-design-and-hillclimbing-with-claude","title":"Automating eval design and hillclimbing with Claude","subtitle":null,"summary":"Lance Martin (claude.dev) explains principles for production-like evals with held-out sets, then shows how the claude-api skill’s build-eval and hillclimb commands automate design and overfitting-aware improvement—including cost and performance case studies.","content_type":"tutorial","language":"en","canonical_url":"https://claude.dev/blog/automating-eval-design-and-hillclimbing/","author":{"name":"Lance Martin","url":"https://claude.dev/blog/automating-eval-design-and-hillclimbing/","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":"Tutorials","slug":"tutorials","url":"https://listedarticles.com/topics/tutorials"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"Software Engineering","slug":"software-engineering","url":"https://listedarticles.com/topics/software-engineering"}],"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":462,"reading_minutes":2,"published_at":"2026-09-28T12:00:00.000Z","added_at":"2026-09-30T00:16:07.307Z","updated_at":"2026-09-30T00:16:07.307Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/automating-eval-design-and-hillclimbing-with-claude","markdown_url":"https://listedarticles.com/articles/automating-eval-design-and-hillclimbing-with-claude.md","example":false,"citation":"Lance Martin, Anthropic. \"Automating eval design and hillclimbing with Claude.\" 28 Sept 2026. https://claude.dev/blog/automating-eval-design-and-hillclimbing/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://claude.dev/blog/automating-eval-design-and-hillclimbing/"},"snippet":null,"score":null},{"slug":"turn-glm-5-3-flash-into-a-jev-like-system-one-model","title":"Turn GLM-5.3-Flash into a Jev-like System One model","subtitle":null,"summary":"Johannes Hötter walks through turning GLM-5.3-Flash into a fast Jev-like “System One” decision model—typed options with probabilities in a single forward pass, matching Jev’s accuracy and speed.","content_type":"tutorial","language":"en","canonical_url":"https://www.privatemode.ai/blog/system-one-from-glm-flash","author":{"name":"Johannes Hötter","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Private Mode AI","url":"https://www.privatemode.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":"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":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":2426,"reading_minutes":11,"published_at":"2026-09-27T03:09:36.533Z","added_at":"2026-09-27T03:09:36.533Z","updated_at":"2026-09-27T03:09:36.533Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/turn-glm-5-3-flash-into-a-jev-like-system-one-model","markdown_url":"https://listedarticles.com/articles/turn-glm-5-3-flash-into-a-jev-like-system-one-model.md","example":false,"citation":"Johannes Hötter, Private Mode AI. \"Turn GLM-5.3-Flash into a Jev-like System One model.\" 27 Sept 2026. https://www.privatemode.ai/blog/system-one-from-glm-flash (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.privatemode.ai/blog/system-one-from-glm-flash"},"snippet":null,"score":null},{"slug":"a-jev-like-wrapper-for-llms-including-vision-models","title":"A Jev-like wrapper for LLMs, including vision models","subtitle":null,"summary":"Allan shows a small single-function Jev-style wrapper for LLMs that also handles vision models, with practical code for local and API backends.","content_type":"tutorial","language":"en","canonical_url":"http://allanrbo.blogspot.com/2026/09/a-jev-like-wrapper-for-llms-including.html","author":{"name":"Allan R. Bo","url":"http://allanrbo.blogspot.com/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Allan's Blog","url":"http://allanrbo.blogspot.com/","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":"Tutorial","slug":"tutorial","url":"https://listedarticles.com/topics/tutorial"},{"name":"Programming","slug":"programming","url":"https://listedarticles.com/topics/programming"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1575,"reading_minutes":7,"published_at":"2026-09-26T12:00:00.000Z","added_at":"2026-09-26T06:12:53.038Z","updated_at":"2026-09-26T06:12:53.038Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/a-jev-like-wrapper-for-llms-including-vision-models","markdown_url":"https://listedarticles.com/articles/a-jev-like-wrapper-for-llms-including-vision-models.md","example":false,"citation":"Allan R. Bo, Allan's Blog. \"A Jev-like wrapper for LLMs, including vision models.\" 26 Sept 2026. http://allanrbo.blogspot.com/2026/09/a-jev-like-wrapper-for-llms-including.html (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"http://allanrbo.blogspot.com/2026/09/a-jev-like-wrapper-for-llms-including.html"},"snippet":null,"score":null},{"slug":"mixture-of-experts-moe-for-backend-engineers","title":"Mixture of Experts (MoE) for Backend Engineers","subtitle":null,"summary":"A detailed visual guide to token routing, expert batching, weighted combination, and the memory and communication tradeoffs of MoE serving. Suppose a model has dozens of feed-forward subnetworks, but each token uses only two of them. The arithmetic per token can stay modest while the total weight set grows. Now place that model on eight GPUs. If every GPU stores all experts, memory can become the limit; if experts are split across GPUs, token activations must travel to whichever GPU owns their…","content_type":"tutorial","language":"en","canonical_url":"https://kurtzhao.com/posts/mixture-of-experts-for-backend-engineers/","author":{"name":"Kurt Zhao","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":null,"url":"https://kurtzhao.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":"Engineering","slug":"engineering","url":"https://listedarticles.com/topics/engineering"},{"name":"Infrastructure","slug":"infrastructure","url":"https://listedarticles.com/topics/infrastructure"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":3515,"reading_minutes":15,"published_at":"2026-09-26T02:53:00.000Z","added_at":"2026-09-26T12:16:10.964Z","updated_at":"2026-09-26T12:16:10.964Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/mixture-of-experts-moe-for-backend-engineers","markdown_url":"https://listedarticles.com/articles/mixture-of-experts-moe-for-backend-engineers.md","example":false,"citation":"Kurt Zhao. \"Mixture of Experts (MoE) for Backend Engineers.\" 26 Sept 2026. https://kurtzhao.com/posts/mixture-of-experts-for-backend-engineers/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://kurtzhao.com/posts/mixture-of-experts-for-backend-engineers/"},"snippet":null,"score":null},{"slug":"local-ai-on-a-12-gb-gpu-what-survived-testing-and-how-to-set-it-up","title":"Local AI on a 12 GB GPU: what survived testing, and how to set it up","subtitle":null,"summary":"Hands-on notes testing local AI models on a 12 GB RTX 3060: which stacks fit in VRAM, how context length decides spills to CPU, and a practical setup that survived the author’s trials.","content_type":"tutorial","language":"en","canonical_url":"https://www.akashdamle.in/blog/local-ai-on-a-12gb-gpu","author":{"name":"Akash Damle","url":"https://www.akashdamle.in/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Akash Damle","url":"https://www.akashdamle.in/","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":"Hardware","slug":"hardware","url":"https://listedarticles.com/topics/hardware"},{"name":"Tutorials","slug":"tutorials","url":"https://listedarticles.com/topics/tutorials"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":3307,"reading_minutes":14,"published_at":"2026-09-25T12:00:00.000Z","added_at":"2026-09-28T06:19:19.809Z","updated_at":"2026-09-28T06:19:19.809Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/local-ai-on-a-12-gb-gpu-what-survived-testing-and-how-to-set-it-up","markdown_url":"https://listedarticles.com/articles/local-ai-on-a-12-gb-gpu-what-survived-testing-and-how-to-set-it-up.md","example":false,"citation":"Akash Damle, Akash Damle. \"Local AI on a 12 GB GPU: what survived testing, and how to set it up.\" 25 Sept 2026. https://www.akashdamle.in/blog/local-ai-on-a-12gb-gpu (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.akashdamle.in/blog/local-ai-on-a-12gb-gpu"},"snippet":null,"score":null},{"slug":"why-updatedinput-in-a-pretooluse-hook-doesnt-rewrite-the-command","title":"Why updatedInput in a PreToolUse Hook Doesn’t Rewrite the Command","subtitle":null,"summary":"A deep dive into Claude Code PreToolUse hooks: why returning updatedInput does not rewrite the shell command, and how permission decisions actually work.","content_type":"tutorial","language":"en","canonical_url":"https://mer.vin/news/why-updatedinput-in-a-pretooluse-hook-doesnt-rewrite-the-command/","author":{"name":"Mervin Praison","url":"https://mer.vin/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"mer.vin","url":"https://mer.vin/","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":"Programming","slug":"programming","url":"https://listedarticles.com/topics/programming"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":3840,"reading_minutes":17,"published_at":"2026-09-25T11:46:46.000Z","added_at":"2026-09-26T09:19:25.724Z","updated_at":"2026-09-26T09:19:25.724Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/why-updatedinput-in-a-pretooluse-hook-doesnt-rewrite-the-command","markdown_url":"https://listedarticles.com/articles/why-updatedinput-in-a-pretooluse-hook-doesnt-rewrite-the-command.md","example":false,"citation":"Mervin Praison, mer.vin. \"Why updatedInput in a PreToolUse Hook Doesn’t Rewrite the Command.\" 25 Sept 2026. https://mer.vin/news/why-updatedinput-in-a-pretooluse-hook-doesnt-rewrite-the-command/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://mer.vin/news/why-updatedinput-in-a-pretooluse-hook-doesnt-rewrite-the-command/"},"snippet":null,"score":null},{"slug":"how-forge-structures-requests-for-prompt-cache-reuse","title":"How Forge Structures Requests for Prompt Cache Reuse","subtitle":null,"summary":"Mohit Ranka explains how Forge, an open-source terminal-first AI IDE, restructures its agent harness requests—stable prefixes, message ordering, history persistence and cache hints—to maximise provider prompt-cache reuse, and how request snapshots plus usage tracking make cache behaviour observable.","content_type":"tutorial","language":"en","canonical_url":"https://www.mohitranka.com/blog/how-forge-structures-requests-for-prompt-cache-reuse/","author":{"name":"Mohit Ranka","url":"https://www.mohitranka.com/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Mohit Ranka","url":"https://www.mohitranka.com/","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":"Developer Tools","slug":"developer-tools","url":"https://listedarticles.com/topics/developer-tools"},{"name":"Performance","slug":"performance","url":"https://listedarticles.com/topics/performance"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1298,"reading_minutes":6,"published_at":"2026-09-24T04:30:00.000Z","added_at":"2026-10-12T08:20:40.053Z","updated_at":"2026-10-12T08:20:40.053Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/how-forge-structures-requests-for-prompt-cache-reuse","markdown_url":"https://listedarticles.com/articles/how-forge-structures-requests-for-prompt-cache-reuse.md","example":false,"citation":"Mohit Ranka, Mohit Ranka. \"How Forge Structures Requests for Prompt Cache Reuse.\" 24 Sept 2026. https://www.mohitranka.com/blog/how-forge-structures-requests-for-prompt-cache-reuse/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.mohitranka.com/blog/how-forge-structures-requests-for-prompt-cache-reuse/"},"snippet":null,"score":null},{"slug":"getting-the-most-out-of-opus-5-5-in-claude-and-claude-code","title":"Getting the most out of Opus 5.5 in Claude and Claude Code","subtitle":null,"summary":"Addy Osmani shares practical prompting, long-run steering, and verification tips for Anthropic’s Opus 5.5 model in Claude apps and Claude Code.","content_type":"tutorial","language":"en","canonical_url":"https://claude.dev/blog/getting-the-most-out-of-opus-5-5/","author":{"name":"Addy Osmani","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Claude","url":null,"listing_slug":"claude","listing":{"slug":"claude","name":"Claude","listing_type":"product","url":"https://listedstartups.com/products/claude"}},"topics":[{"name":"ai","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"llms","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"tutorials","slug":"tutorials","url":"https://listedarticles.com/topics/tutorials"},{"name":"developer-tools","slug":"developer-tools","url":"https://listedarticles.com/topics/developer-tools"},{"name":"productivity","slug":"productivity","url":"https://listedarticles.com/topics/productivity"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":2449,"reading_minutes":11,"published_at":"2026-09-22T12:00:00.000Z","added_at":"2026-10-03T20:16:58.821Z","updated_at":"2026-10-03T20:16:58.821Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/getting-the-most-out-of-opus-5-5-in-claude-and-claude-code","markdown_url":"https://listedarticles.com/articles/getting-the-most-out-of-opus-5-5-in-claude-and-claude-code.md","example":false,"citation":"Addy Osmani, Claude. \"Getting the most out of Opus 5.5 in Claude and Claude Code.\" 22 Sept 2026. https://claude.dev/blog/getting-the-most-out-of-opus-5-5/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://claude.dev/blog/getting-the-most-out-of-opus-5-5/"},"snippet":null,"score":null},{"slug":"heretic-tutorial-automatic-censorship-removal-for-language-models","title":"Heretic tutorial: automatic censorship removal for language models","subtitle":null,"summary":"A hands-on tutorial for Heretic, an open-source tool that automatically removes refusal/censorship behaviors from language models—setup, workflow, and what to watch for.","content_type":"tutorial","language":"en","canonical_url":"https://heretic-project.org/tutorial","author":{"name":"p-e-w","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Heretic","url":"https://heretic-project.org/","listing_slug":null,"listing":null},"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":1688,"reading_minutes":7,"published_at":"2026-09-22T09:08:16.312Z","added_at":"2026-09-22T09:08:16.312Z","updated_at":"2026-09-22T09:08:16.312Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/heretic-tutorial-automatic-censorship-removal-for-language-models","markdown_url":"https://listedarticles.com/articles/heretic-tutorial-automatic-censorship-removal-for-language-models.md","example":false,"citation":"p-e-w, Heretic. \"Heretic tutorial: automatic censorship removal for language models.\" 22 Sept 2026. https://heretic-project.org/tutorial (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://heretic-project.org/tutorial"},"snippet":null,"score":null},{"slug":"transformer-explainer-llm-transformer-model-visually-explained","title":"Transformer Explainer: LLM Transformer Model Visually Explained","subtitle":null,"summary":"Georgia Tech’s Polo Club walks through GPT-2’s Transformer stack—embeddings, multi-head attention, MLP, sampling—with an interactive in-browser model for learning how next-token prediction works.","content_type":"tutorial","language":"en","canonical_url":"https://poloclub.github.io/transformer-explainer/","author":{"name":"Polo Club of Data Science, Georgia Tech","url":"https://poloclub.github.io/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Polo Club of Data Science","url":"https://poloclub.github.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":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"},{"name":"Education","slug":"education","url":"https://listedarticles.com/topics/education"},{"name":"Programming","slug":"programming","url":"https://listedarticles.com/topics/programming"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":827,"reading_minutes":4,"published_at":"2026-09-22T03:12:31.905Z","added_at":"2026-09-22T03:12:31.905Z","updated_at":"2026-09-22T03:12:31.905Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/transformer-explainer-llm-transformer-model-visually-explained","markdown_url":"https://listedarticles.com/articles/transformer-explainer-llm-transformer-model-visually-explained.md","example":false,"citation":"Polo Club of Data Science, Georgia Tech, Polo Club of Data Science. \"Transformer Explainer: LLM Transformer Model Visually Explained.\" 22 Sept 2026. https://poloclub.github.io/transformer-explainer/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://poloclub.github.io/transformer-explainer/"},"snippet":null,"score":null},{"slug":"jev-in-25-lines-of-python","title":"Jev in 25 lines of Python","subtitle":null,"summary":"NobodyWho shows a local, 25-line Python sketch of Jev-style decision models: load a small GGUF, score labeled choices from logits, and print calibrated-looking probabilities without sending data to an API.","content_type":"tutorial","language":"en","canonical_url":"https://www.nobodywho.ai/posts/jev-in-25-lines/","author":{"name":"Duarte O.Carmo","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"NobodyWho","url":"https://www.nobodywho.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":"Programming","slug":"programming","url":"https://listedarticles.com/topics/programming"},{"name":"Open Source","slug":"open-source","url":"https://listedarticles.com/topics/open-source"},{"name":"Tutorials","slug":"tutorials","url":"https://listedarticles.com/topics/tutorials"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":419,"reading_minutes":2,"published_at":"2026-09-22T00:00:00.000Z","added_at":"2026-09-23T09:10:18.443Z","updated_at":"2026-09-23T09:10:18.443Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/jev-in-25-lines-of-python","markdown_url":"https://listedarticles.com/articles/jev-in-25-lines-of-python.md","example":false,"citation":"Duarte O.Carmo, NobodyWho. \"Jev in 25 lines of Python.\" 22 Sept 2026. https://www.nobodywho.ai/posts/jev-in-25-lines/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.nobodywho.ai/posts/jev-in-25-lines/"},"snippet":null,"score":null},{"slug":"aie-2-1-building-it-a-conversation-engine-where-the-llm-remembers","title":"aie_2.1: building it — a conversation engine where the LLM 'remembers'","subtitle":null,"summary":"Meraki builds a Python conversation engine that shows how LLMs fake memory: every turn resends the full history so the model appears to remember, with practical notes on context and design.","content_type":"tutorial","language":"en","canonical_url":"https://heymeraki.substack.com/p/aie_21-building-it","author":{"name":"meraki","url":"https://heymeraki.substack.com/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"heyy.meraki","url":"https://heymeraki.substack.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":"Programming","slug":"programming","url":"https://listedarticles.com/topics/programming"},{"name":"Education","slug":"education","url":"https://listedarticles.com/topics/education"},{"name":"Tutorials","slug":"tutorials","url":"https://listedarticles.com/topics/tutorials"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":2124,"reading_minutes":9,"published_at":"2026-09-19T17:09:19.000Z","added_at":"2026-09-19T18:16:06.082Z","updated_at":"2026-09-19T18:16:06.082Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/aie-2-1-building-it-a-conversation-engine-where-the-llm-remembers","markdown_url":"https://listedarticles.com/articles/aie-2-1-building-it-a-conversation-engine-where-the-llm-remembers.md","example":false,"citation":"meraki, heyy.meraki. \"aie_2.1: building it — a conversation engine where the LLM 'remembers'.\" 19 Sept 2026. https://heymeraki.substack.com/p/aie_21-building-it (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://heymeraki.substack.com/p/aie_21-building-it"},"snippet":null,"score":null},{"slug":"model-context-protocol-with-spring-ai-building-mcp-clients-and-servers-in-java","title":"Model Context Protocol with Spring AI, Building MCP Clients and Servers in Java","subtitle":null,"summary":"Ayush Shrivastava walks through building MCP clients and servers with Spring AI in Java: tool discovery, protocol basics, and wiring MCP into agentic Spring applications beyond a basic demo.","content_type":"tutorial","language":"en","canonical_url":"https://dev.to/ayshriv/model-context-protocol-with-spring-ai-building-mcp-clients-and-servers-in-java-2146","author":{"name":"Ayush Shrivastava","url":"https://dev.to/ayshriv","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"DEV Community","url":"https://dev.to/","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":"Programming","slug":"programming","url":"https://listedarticles.com/topics/programming"},{"name":"Developer Tools","slug":"developer-tools","url":"https://listedarticles.com/topics/developer-tools"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":2972,"reading_minutes":13,"published_at":"2026-09-19T00:00:00.000Z","added_at":"2026-09-30T18:16:01.019Z","updated_at":"2026-09-30T18:16:01.019Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/model-context-protocol-with-spring-ai-building-mcp-clients-and-servers-in-java","markdown_url":"https://listedarticles.com/articles/model-context-protocol-with-spring-ai-building-mcp-clients-and-servers-in-java.md","example":false,"citation":"Ayush Shrivastava, DEV Community. \"Model Context Protocol with Spring AI, Building MCP Clients and Servers in Java.\" 19 Sept 2026. https://dev.to/ayshriv/model-context-protocol-with-spring-ai-building-mcp-clients-and-servers-in-java-2146 (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://dev.to/ayshriv/model-context-protocol-with-spring-ai-building-mcp-clients-and-servers-in-java-2146"},"snippet":null,"score":null}],"total":26,"count":20,"next_offset":20,"has_more":true,"query":{"q":null,"content_type":"tutorial","topic":"llms","publisher":null,"about":null,"author":null,"language":null,"sort":"newest","limit":20,"offset":0}}