A developer has released the first public prototype of LIMEN Runtime Audit, an open-source toolkit for inspecting layer-wise activation trajectories in open-weight language models. The toolkit measure…
Hugging Face released a new tool called 'Am I in the Stack?' that allows users to check if their code or data is included in The Stack, a large dataset used to train AI models. The tool, available as …
The REFUTE dataset and leaderboard, hosted on Hugging Face by BGPT-OFFICIAL, provide a judge-free evaluation board for science paper summaries, addressing the failure mode where LLM-as-a-judge re-impo…
A case study of three frontier large language models (GPT, Claude, and Gemini) found that two models exhibited epistemic drift during extended business-planning conversations, with one generating fabr…
ThetaScan v0.1, a fixed-state nonlinear token mixer released by developer aim-do, achieves competitive bits-per-byte (BPB) on a 17M language-model experiment at step 7,500, with raw BPB of 1.2327 for …
PathMap AI, developed by investigator Joshua Dungan, identified high amylose maize starch as a potential non-invasive tool to improve outcomes in traumatic brain injury and hypoxic neurovascular damag…
A developer recommends building a structured knowledge base from website content using chunking, embeddings, and a vector database for retrieval-augmented generation (RAG) to improve LLM search functi…
A lightweight AI assistant is recommended over a rule-based chatbot for small businesses handling simple customer queries, as it better understands varied phrasing through semantic search. The approac…
A Hugging Face user recommends GLM 5.2 as the best open-source LLM for customer support chatbots, citing its advanced capabilities and relatively low cost to run. The user acknowledges their beginner …
A community analysis of local AI coding agent performance identifies several optimization settings for Ubuntu users running llama.cpp/SYCL with dual Intel Arc Pro B70 GPUs and the Qwen3.6-27B model. K…
A researcher has built an Attractor Map for TinyLlama that tracks the trajectory of hidden states during text generation, revealing that model trajectories repeatedly visit a limited number of dynamic…
A developer investigating the real-world performance of 7B–14B domain-specific LLMs finds a gap between the optimistic claims of frontier models like ChatGPT, Claude, and Gemini and the cautious feedb…
A developer implementing an LSTM in C/C++ for audio generation is experimenting with activation functions, including using no activation and a quadratic shaping function, and reports faster learning b…
A developer has built an upgraded version of the classic ELIZA chatbot using a sparse autoencoder with a large latent memory layer, achieving logarithmic memory scaling and resistance to catastrophic …
The Huggy Database, the largest open dataset of French horse racing, has been released on the Hugging Face Hub, containing 356,371 unique races from 1996 to 2026 with approximately 5 million runners a…
A user reports a possible billing bug with Hugging Face's Inference Providers, where every request has been charged a flat $0.01 for the last two days regardless of model or actual usage, based on scr…
OpenInfer has requested to register as an official Hugging Face Inference Provider, offering an OpenAI-compatible inference API focused on high-performance, cost-efficient model serving across heterog…
Developer AminMusah built Forge (modelplayground.dev), an open-source browser playground for Hugging Face models that runs models locally via transformers.js and WebGPU, while a separate code model ge…
Hugging Face has integrated Nunchaku 4-bit diffusion inference natively into Diffusers, enabling users to load quantized checkpoints with a simple from_pretrained() call and no local CUDA compilation.…
A proposed AI agent pre-execution checklist framework aims to prevent errors by requiring verification of unknown information before any action is taken, addressing instruction and action definition g…