[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-long-context":3},{"tag":4,"articles":11,"peer_article_count":115},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"9bacdf64-f75d-4c59-a836-d469cbe34dfc","long context","long-context",8,"長上下文指的是模型在一次推理中維持大量前後文的能力，牽涉記憶壓縮、檢索、快權重更新與推理穩定性。從 1M\u002F2M token 視窗到 state-space、TTT 與 agent 工作流，都是它的實作重點。","Long context refers to an LLM’s ability to keep and use very large histories in one pass, shaping memory design, retrieval, fast-weight updates, and stable reasoning. It shows up in 1M-2M token windows, state-space memory, TTT, and agent workflows.",[12,21,29,36,43,50,58,65,73,80,87,94,101,108],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"6288131d-64e3-47ff-aeec-add641c952e2","kimi-long-context-models-moonshot-ai-en","Kimi’s long-context push keeps getting bigger","Moonshot AI’s Kimi chatbot keeps expanding context, agents, and model size, with Kimi K2.5 arriving in January 2026.","model-release","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782231491199-wiwi.png","en","2026-06-23T16:17:38.462613+00:00",{"id":22,"slug":23,"title":24,"summary":25,"category":26,"image_url":27,"cover_image":27,"language":19,"created_at":28},"221ce4cc-ac8a-486b-97ed-b5ddaf6c6cf7","kimi-k2-6-turns-agents-into-a-swarm-en","Kimi K2.6 turns agents into a swarm","Kimi K2.6 is an open-source multimodal agent model for long coding runs, UI generation, and swarm-style task orchestration.","ai-agent","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781824696228-ongx.png","2026-06-18T23:17:48.267558+00:00",{"id":30,"slug":31,"title":32,"summary":33,"category":17,"image_url":34,"cover_image":34,"language":19,"created_at":35},"ccc46975-50d1-4ece-8fd3-c082bf4858ae","self-host-minimax-m3-gpu-cloud-en","Self-host MiniMax M3 on GPU cloud","MiniMax M3 brings 229.9B MoE weights, 1M context, and multimodal output, but it needs serious GPU memory to run.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781716680837-ikof.png","2026-06-17T17:17:35.800599+00:00",{"id":37,"slug":38,"title":39,"summary":40,"category":17,"image_url":41,"cover_image":41,"language":19,"created_at":42},"17a7dc8b-25e4-4993-b0dd-b23733390007","gemma-4-256k-context-open-models-en","Gemma 4 brings 256K context to open models","Google’s Gemma 4 adds text, image, and audio input, plus up to 256K context and five model sizes for local or server use.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781686085345-8dgk.png","2026-06-17T08:47:34.623499+00:00",{"id":44,"slug":45,"title":46,"summary":47,"category":17,"image_url":48,"cover_image":48,"language":19,"created_at":49},"22137409-904c-49c4-bebb-1b4683438c6f","minimax-m3-1m-token-coding-power-en","MiniMax M3 adds 1M-token coding power","MiniMax M3 brings coding and agent features, a 1 million-token context window, and multimodal input to the company’s flagship model.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781295476573-19e8.png","2026-06-12T20:17:28.486889+00:00",{"id":51,"slug":52,"title":53,"summary":54,"category":55,"image_url":56,"cover_image":56,"language":19,"created_at":57},"cb48de54-dfdc-4fe0-adde-e5e3465c57bd","2026-llm-paper-lists-better-than-feeds-en","2026 LLM paper lists are a better research tool than feeds","Curated LLM paper lists beat raw feeds because they turn scattered research into usable context.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781258572644-me3b.png","2026-06-12T10:02:16.943321+00:00",{"id":59,"slug":60,"title":61,"summary":62,"category":17,"image_url":63,"cover_image":63,"language":19,"created_at":64},"9d15f962-739d-44f8-a7f9-11bca64d38e0","best-kimi-models-2026-k2-5-vs-k2-thinking-en","Best Kimi Models in 2026: K2.5 vs K2 Thinking","Kimi K2.5 leads Moonshot AI’s 2026 lineup with 256K context, 1T parameters, Agent Swarm Mode, and low API pricing.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780770786284-shy0.png","2026-06-06T18:32:39.779504+00:00",{"id":66,"slug":67,"title":68,"summary":69,"category":70,"image_url":71,"cover_image":71,"language":19,"created_at":72},"6d035ac9-0dc7-48bd-b888-161a30e1b9f8","gemini-turns-googles-ai-stack-into-one-app-en","Gemini turns Google’s AI stack into one app","A developer’s breakdown of Gemini’s rollout, model tiers, and why Google folded search, app, and Vertex AI into one AI surface.","tools","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780700608803-93oz.png","2026-06-05T23:02:59.992521+00:00",{"id":74,"slug":75,"title":76,"summary":77,"category":17,"image_url":78,"cover_image":78,"language":19,"created_at":79},"6c57f6bf-1023-4a22-a6c0-013bd88ac3d1","minimax-m1-open-hybrid-attention-reasoning-model-en","MiniMax-M1 brings 1M-token open reasoning model","MiniMax released M1, an open-source reasoning model with 1M-token context, 80k output, and low-cost API pricing.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778797872005-z8uk.png","2026-05-14T22:30:39.599473+00:00",{"id":81,"slug":82,"title":83,"summary":84,"category":55,"image_url":85,"cover_image":85,"language":19,"created_at":86},"c1aac50e-0c41-471c-946e-329652f04565","sessa-attention-inside-state-space-memory-en","Sessa: Attention and State-Space Memory for Long Context","Sessa mixes attention with recurrent state-space feedback to improve long-context recall, with power-law memory tails and strong benchmark results.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776751621598-1d0l.png","2026-04-21T06:06:37.564074+00:00",{"id":88,"slug":89,"title":90,"summary":91,"category":55,"image_url":92,"cover_image":92,"language":19,"created_at":93},"b65aeb57-d1b7-4cdd-adb9-464b8cfbfe0a","in-place-ttt-llms-adapt-at-inference-en","In-Place TTT Lets LLMs Adapt at Inference","A new test-time training setup lets LLMs update fast weights in place, aiming for better long-context adaptation without full retraining.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775628426736-0dm6.png","2026-04-08T06:06:33.249426+00:00",{"id":95,"slug":96,"title":97,"summary":98,"category":17,"image_url":99,"cover_image":99,"language":19,"created_at":100},"c0e85793-59d6-47ba-9c97-f856a4544baf","grok-420-xai-flagship-model-explained-en","Grok 4.20: xAI's new flagship model explained","xAI’s Grok 4.20 adds a 2M-token context window, multi-agent reasoning, and API pricing from $2 per million input tokens.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775175184959-ok8i.png","2026-04-03T00:12:38.289208+00:00",{"id":102,"slug":103,"title":104,"summary":105,"category":17,"image_url":106,"cover_image":106,"language":19,"created_at":107},"04e78fe1-7f49-40db-bfb2-7bb4b3579276","gemini-3-1-pro-googles-top-model-in-numbers-en","Gemini 3.1 Pro: Google’s new top model in numbers","Gemini 3.1 Pro posts 77.1% on ARC-AGI-2, 94.3% on GPQA Diamond, and a 1M-token context window, while keeping Gemini 3 pricing.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775153582956-qese.png","2026-04-02T18:12:42.161483+00:00",{"id":109,"slug":110,"title":111,"summary":112,"category":55,"image_url":113,"cover_image":113,"language":19,"created_at":114},"27f0d044-b9f9-4a58-99e8-1a181ea32f19","universal-yoco-efficient-depth-scaling-en","Universal YOCO aims to scale depth without cache bloat","YOCO-U mixes recursive computation with efficient attention to scale LLM depth while keeping inference overhead and KV cache growth in check.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775115621645-wqql.png","2026-04-02T06:06:26.960639+00:00",13]