THE INTERNET IS THINKING
Earlier sources: Artificial Intelligence
Artificial intelligence covers systems that learn from data, generate content, perceive their surroundings, or act toward a goal. Follow model research, agent tooling, evaluation, and the infrastructure used to build and run these systems.
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 ↗5951 classified signals in the fourteen-day window. Recent momentum: steady. 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
SKILLLITE: Evidence-Guided Malicious Skill Auditing with Compact LLMs ↗
As LLM-based agents perform increasingly complex tasks, Agent Skills have emerged as a flexible mechanism for extending their capabilities. An Agent Skill packages task-specific instructions with executable components and auxiliary resources to provide specialized functionalities. However, the growing adoption of third-party Skills introduces a new supply-chain attack surface. Malicious Skills can embed harmful behaviors that abuse agent privileges and compromise the agent execution environment or accessible resources. Although recent LLM-based malicious Skill auditing approaches have achieved…
- GitHub · Repository created · First archived
12-Twelve-12/robolings ↗
Small exercises for robot learning, rustlings style: kinematics, dexterous hands, control, diffusion policy, flow matching. NumPy only.
- Hacker News · Posted on Hacker News · First archived
OpenAI: Tomorrow we are re-opening the Pro $200 subscription ↗
Hacker News discussion.
- arXiv · Published · First archived
Safer Content or Firmer Refusals? A Hybrid Perturbation Defense for Alignment under Harmful Fine-tuning ↗
Fine-tuning-as-a-service lets users adapt a safety-aligned language model to their own data, but it also creates a harmful fine-tuning attack surface: a small amount of harmful data mixed into an otherwise benign fine-tuning set can degrade the model's alignment. Two recent alignment-stage defenses address this problem at different levels of the model. Vaccine improves the robustness of hidden embeddings to the representation shifts induced by harmful fine-tuning, whereas Booster simulates harmful weight updates and attenuates their effect during alignment. We investigate whether these mechani…
- Hacker News · Posted on Hacker News · First archived
When can we say AI made a scientific discovery? ↗
Hacker News discussion.
- Hugging Face · Model / dataset date · First archived
sqrtask/tamagotchi-models — model update ↗
# Модели офлайн-тамагочи для браузера Сборки, подготовленные для игры, где всё работает локально в браузере: маленькая LLM отвечает на вопросы о предмете («это предмет?», «влезает в куб 1 м?»), переводит слово на английский и описывает свойства, а SDXS рисует иконку. Исходные модели — чужие, здесь лежат только наши переделки для веба. Замеры и код — в репозитории проекта (`appendix/tamagotchi/` и `appendix/small_imagegen/`). Все файлы отдаются с CDN Hugging Face по частям (HTTP Range, ответ 206) и с `Access-Control-Allow-Origin: *`, так что их можно качать прямо из браузера в несколько потоков
- Hugging Face · Model / dataset date · First archived
jinghao1632/bit-jev-2b-distilled — model update ↗
# bit-jev-2b-distilled [English model card](README.en.md) · [源码仓库](https://github.com/Zeaulo/bit-jev) · [pip 安装](https://pypi.org/project/bit-jev/) · [ModelScope 镜像](https://www.modelscope.cn/models/JingHao9616/bit-jev-2b-distilled) · [在线测试](https://jinghao9616-bit-jev-demo.ms.show/) · [Hugging Face 双语入口](https://huggingface.co/spaces/jinghao1632/bit-jev-demo) 中英双语测试页可修改客服场景并查看真实模型的选项、概率与原生计算耗时。ModelScope 免费 CPU 空间执行推理；Hugging Face 免费静态 Space 嵌入该空间。首次请求的模型下载与加载不计入页面显示的推理耗时。  在运行推理的同一个 Python 3.11/3.12 环境中安装并核对版本： ```bash pip install bit-jev -i https:
- arXiv · Published · First archived
Does the Unsafe Gradient Survive a Conversation? On the Fragility of Gradient-Based Jailbreak Detection in Multi-Turn Dialogue ↗
Safety-aligned language models are commonly deployed as multi-turn assistants, which lets adversaries spread unsafe intent across several user turns instead of a single prompt. Gradient-based jailbreak detectors such as GradSafe were developed for single prompts: they score an input by the alignment between its induced gradient and a fixed unsafe reference direction, and their effectiveness in multi-turn dialogue remains unclear. We conduct a controlled evaluation of gradient-based jailbreak detection in multi-turn settings. We extend GradSafe with a Context Window Scanner that applies the det…
- arXiv · Published · First archived
DSWM: Decomposed Spatio-Temporal World Model for Demand-Driven UAV Base Station Repositioning ↗
Uncrewed aerial vehicle base stations (UAV-BSs) are expected to cover traffic demand that shifts across space and time, yet most repositioning schemes either re-solve an optimization problem per slot or learn reactive policies without an explicit demand model. We cast demand-driven fleet repositioning as latent-space decision-time planning and propose DSWM, a decomposed spatio-temporal world model: an agentic controller that perceives the demand field through a rolling observation window, retains operational context in a latent recurrent state, reasons about candidate motions by imagined rollo…
- Hacker News · Posted on Hacker News · First archived
As AI models go rogue, do you still trust OpenAI and Anthropic to stop them? ↗
Hacker News discussion.
Live window recorded . This is the ingestion observation time, not the publication or discovery date of each source.
How to assess evidence about Artificial Intelligence
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 ↗
Follow a thread
Explore related regions
These navigation suggestions are part of the map’s editorial structure, rather than measured evidence of a connection.