Topic: age
136 stories found
Today
Recognition, Simulation, and Refusal: A Contamination-Aware Study of Classic Psychological Effects in LLM Agents
The study PsyAgentBench re-runs classic psychology experiments on LLMs to assess their susceptibility to human biases without attributing those biases directly to the models, highlighting the need for contamination-aware analysis. This matters as it provides a framework to understand and mitigate potential psychological effect mimicry in AI systems.
Yesterday

How V7 gives AI agents institutional memory
V7 uses GPT-5.6 to compile company files into a coherent knowledge base for AI agents, enhancing their ability to handle complex tasks with accurate context. This innovation matters because it gives AI systems institutional memory, improving their efficiency and effectiveness in professional settings.
NousResearch releases: Hermes Agent v0.21.4 (v2026.9.21)
Hermes Agent version v0.21.4 was released on September 21, 2026, consolidating approximately 1,800 merged pull requests to provide a stable release for various deployment environments, including Docker images and Hermes Cloud services.
macOS 27: Workaround to avoid downloading AI models and save storage
Apple released an update for macOS that includes a workaround to prevent the automatic download of AI models, helping users conserve storage space. This update is significant as it addresses user concerns about storage usage by AI features without compromising functionality.
ggml/llama.cpp releases: b11081
The ggml/llama.cpp project released a new version with updates to make tensor data standard deviation configurable and added more examples to the documentation, enhancing flexibility and usability for developers. These changes are significant as they improve the toolkit's adaptability and user-friendliness in handling large language model architectures.
Do small language models know what they don't know?
Researchers investigated ways to enhance the accuracy of small language models (with less than 3 billion parameters) using entropy-based confidence signals, finding potential improvements for models running on consumer hardware. This matters because it could make advanced language capabilities more accessible on standard devices.
LoRA Enhanced Contrastive Learning with SAS Vision Transformers
A new method called LoRA Enhanced Contrastive Learning with SAS Vision Transformers has been developed to improve automatic target recognition in synthetic aperture sonar, addressing limitations such as sparse target data and background noise. This advancement is crucial for enhancing naval capabilities through more efficient and accurate underwater target identification.
Sunday, September 20, 2026
langgenius/dify — Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cl
Agentic offers a collaborative workspace for building AI workflows and RAG pipelines with extensive model and tool support, enabling seamless deployment options from cloud to self-hosted environments, facilitating rapid transition from prototypes to production.

Qwen Image 2.1
Qwen Image 2.1 is an advanced image generation model developed to enhance text-to-image synthesis capabilities, aiming to provide more detailed and realistic images based on textual descriptions. Its development marks a significant step forward in artificial intelligence for creative content production, potentially revolutionizing fields such as design, entertainment, and marketing by offering more sophisticated visual outputs.
Saturday, September 19, 2026
affaan-m/ECC — The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development f
A new agent harness performance optimization system focusing on skills, instincts, memory, security, and research-first development is being implemented for Claude Code, Codex, Opencode, Cursor, and other similar systems. This update aims to enhance overall efficiency and reliability by improving core functionalities and security measures.
136 of 136 items shown. Sources: 123 days indexed.