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.
- arXiv · Published · First archived
Mizar: A 159M-Parameter Audio-Language Model for Audio Understanding ↗
Audio-language models (ALMs) integrate acoustic perception with the knowledge encoded in language models, enabling contextual understanding of auditory events. Making these capabilities practical on devices with limited memory and computation motivates our focus on small ALMs with fewer than 200M parameters. We introduce a recipe that brings together architecture, data, and three-stage training to build Mizar, a 159.3M-parameter ALM. Its architecture connects a compact CED-Small audio encoder to SmolLM2-135M through a frequency-merging mapper. With supervision drawn from ReasonAQA, AudioMCQ, a…
- GitHub · Repository created · First archived
Nisaka520/JevGuide ↗
弦外之音 —— 微信聊天里的关系进展助手：读屏（无障碍树 / 截屏视觉）→ Jev 判读 + 攻略度 → 聊天模型出 3 条候选回复，攻略度常驻挂在屏幕上。不改微信、不发消息、不注入点击。
- arXiv · Published · First archived
Can LLMs Catch a Rigged Backtest? A Clean-Control Calibration Benchmark ↗
Backtest auditing is a calibration problem: high flaw recall is not useful when the model falsely flags matched clean strategies. We build a 96-item paired benchmark in which every flawed backtest has a clean control that holds strategy, dates, code style, labels, and reporting scaffold fixed while changing one methodology detail. A deterministic scorer separates flaw recall, clean-control false positives, evidence localization, and fix relevance. Over 1440 cached audits from four text endpoints, the primary DeepSeek auditor reaches 100.0\% closed and clean-aware code recall, but open prompts…
- arXiv · Published · First archived
LLM-Assisted Workflow for Structural Difference Visualization in Evolving Software Requirements ↗
This paper presents an LLM-assisted workflow for visualizing structural differences in evolving software require- ments. Implemented in the OntologyWeb environment, the work- flow represents baseline and current requirements as triple-based semantic graphs and supports side-by-side comparison of curated graph snapshots. The comparison view aligns matched entities and uses visual encoding to highlight structural changes.
- arXiv · Published · First archived
Your Model Is Leaking: Covert Information Transfer through LLM Residual Streams ↗
Privacy-sensitive organizations may run large language models (LLMs) in restricted or air-gapped environments while exporting selected diagnostic artifacts. We show that a compromised runtime component can hide sensitive information in intermediate activations that are allowed to leave the restricted environment. An offline observer can recover this information with a simple linear decoder. The attack requires no model retraining or weight modification, no attacker-controlled egress, and no control over the recorder or transfer process. We introduce a residual-stream covert-channel attack that…
- GitHub · Repository created · First archived
zhulinchng/jevper ↗
Jev-shaped (TypeSafe System One) classification wrapper over OpenAI-like clients
- GitHub · Repository created · First archived
ILuce/deqio ↗
Run fast, typed AI decision models behind one API. Choice, score and yes/no decisions with multiple engines and hardware backends.
- GitHub · Repository created · First archived
tswawa/WechatVibe ↗
微信聊天分析工具，支持本地 Laya 与 API 模型，提供意图识别、情绪感知、人物画像、群聊画像、好感度分析和 MBTI 聊天推测。
- GitHub · Repository created · First archived
6Mikao9/jev-native-agent-with-extended-options ↗
Research design for a Jev-native agent system:enable more options than jev provided with virtulization and paging, tool integration, external helper logits Top-k proposals with Jev-controlled fallback ,decision-aware hierarchical memory, and dependency-aware replanning.
- GitHub · Repository created · First archived
amitshekhariitbhu/ai-engineering-course ↗
AI Engineering Course - A free and complete AI Engineering Course to learn AI Engineering step by step - from Machine Learning, Neural Networks, and Transformers to LLMs, Fine-Tuning, RAG, AI Agents, LLM Inference, Evaluation, AI Safety, and AI System Design.
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.