THE INTERNET IS THINKING
Earlier sources: Language models
Language models learn patterns in text and other representations to predict or generate sequences. Follow model releases, training methods, reasoning, evaluation, and deployment research; a benchmark result is specific to its test conditions.
SYMTRI organizes observations from public sources into a living map. Connections reflect shared subject matter; they do not establish causation or endorse a source.
Open in the map ↗450 classified signals in the fourteen-day window. These counts include signals awaiting readable evidence.
Earlier sources
Up to ten sources with readable evidence, ordered by their feed timestamp. These archive sources can be older than the live fourteen-day window. This list is a sample, not a measure of total activity. Dates distinguish paper publication, repository creation, model/dataset activity, Hacker News posts, and KEV catalog additions. “First archived” records when SYMTRI first stored the signal.
- GitHub · Repository created · First archived
john-walks-slow/token-speed-patrol ↗
LLM API 定时测速巡检 + 静态看板（GitHub Actions 免服务器）
- GitHub · Repository created · First archived
MiaoWuNYA/rikkahub-sillytavern-android ↗
安卓AI聊天端:开箱即聊，无损导入酒馆卡，缓存强省用量，Jev 决策，防空回，多维记忆，前端卡支持，QQbot，AI群聊，高定制主题，插件系统，强兼容中转站。手机移动端原生支持/Android AI Chatbox: lossless SillyTavern card import, aggressive cache optimization, Jev decisions, multi-dimensional memory, anti-blank-reply, proactive messages, AI group chat, SillyTavern themes, plugin system, Native mobile.RikkaHub
- GitHub · Repository created · First archived
jimoto-no-llm/bench-of-us ↗
みんなのローカルLLMベンチマーク結果をあつめるレポジトリ
- GitHub · Repository created · First archived
walidboulanouar/awesome-jev-use-cases ↗
Awesome list of TypeSafe AI Jev use cases: 74 demos ranked by likes, 150+ GitHub repos, limits, cost and API examples. CC0
- GitHub · Repository created · First archived
1abobik1/VocabTGBot ↗
полностью бесплатный: без аренды сервера и без платных API. Telegram-бот для заучивания английских слов по карточкам с ИИ генерацией текста или ручным добавлением
- GitHub · Repository created · First archived
Yinsongxu/LLM2Jev ↗
Turn local language models into Jev-style structured decision models. Get results from text and images with prefill alone—no token-by-token decoding required.
- GitHub · Repository created · First archived
kushals256/jevcache ↗
Skip expensive LLM calls when TypeSafe Jev (or local System One) says same intent. OpenAI-compatible local cache proxy — npx @kushalicious/jevcache
- GitHub · Repository created · First archived
SUNNYYUBER/DSH-Tavern-for-Android ↗
Android app that imports your SillyTavern data (cards / worldbooks / presets / chats). Early Alpha — may be unusable. 早期测试版
- GitHub · Repository created · First archived
professorpalmer/bonsai-ada-surgery ↗
Bonsai 2 27B: 262k context (trained max) on 12 GB, 54 to 97 tok/s decode, 2x prefill, q8_0 KV recipe, grammar tool calls 9/9. Same ternary weights. Windows bundle + receipts.
- GitHub · Repository created · First archived
NotXf1le/choosekit ↗
Typed choices and probability distributions from text and images with llama.cpp, Ollama, and OpenRouter
Live window recorded . This is the ingestion observation time, not the publication or discovery date of each source.
How to assess evidence about Language models
Check each original source for its methods, release status, limitations, and supporting data. A repository announcement, a preprint, and a published study provide different kinds of evidence. SYMTRI’s subject classification helps discovery; it does not independently validate the source’s claims.
See the collection and counting methodology ↗ · Read the weekly synthesis ↗
Related threads
Explore related regions
These navigation suggestions are part of the map’s editorial structure, rather than measured evidence of a connection.