A public AI-agent performance record directory has added Hugging Face import support that pulls a user's Spaces and pre-fills draft profiles, but the operator reports the Hub lacks an OIDC attestation…
A discussion post asks where shared project state, task ownership, and accountability should live when multiple AI agents work on the same project, noting Hugging Face already has work around agent fr…
Users of the Hugging Face agents course are reporting that links in the course sidebar return 404 errors, including the URL https://huggingface.co/docs/agents-course/main/en/communication/live1, and t…
ApexSovereign Infrastructure Protocol launched ApexSovereign, a bare-metal GPU compute service it says cuts model fine-tuning and inference overhead by up to 40% by scanning global spot-market pricing…
ApexSovereign launched a real-time GPU compute arbitrage protocol that it says scans global spot-market pricing maps every 1,500 milliseconds to secure underutilized bare-metal hardware and cut model …
A user reports that multiple links in the Hugging Face Agents Course point to an outdated /docs/agents-course/ URL structure and return a "Sorry, we can't find the page you are looking for" error, whi…
Diffusers-workflow now returns a plan block from validate_workflow and POST /api/validate containing a fingerprint of the realized workflow, actual step and iteration counts, required downloads, and a…
A conceptual research proposal introduces the Dynamic Immune-Shunt Architecture (DISA), an experimental framework combining sparse internal monitoring, multi-signal risk estimation, reversible interve…
A Hugging Face community member reported that Zenodo returns a 504 Gateway Time-out when downloading the PxSLU/PxCorpus dataset (Zenodo 6524162), specifically the 375.5 MB pxslu.zip file. A respondent…
The developer of ZYR3.1MoE, an open-weights 9B-parameter multi-agent orchestration model built on a Qwen base, is seeking one or two collaborators for dataset curation, agent orchestration, or fine-tu…
A new photorealism LoRA called Badaramoni Fusion was released for Krea 2 Turbo, using a weight-delta-space fusion algorithm that merges mixed-format LoRA and LoKR adapters into a single portable .safe…
A developer has published a learning repository containing 38 runnable notebooks that teach the Hugging Face stack by progressively removing abstractions, from high-level APIs through fine-tuning, PEF…
An independent developer has released Prism, a language model with an 842KB weight file and 107,776 parameters that runs in a browser and generates text from bigram subword tokens, spelling words rath…
A feature request asks Hugging Face to add a GitHub-style profile README, in which a README.md in a special username/username repository would render automatically on a user's profile page. The reques…
A forum poster clarified that their original proposal was not to use an NVMe SSD as VRAM, but to design future consumer GPUs with an expandable, lower-cost memory tier managed directly by the GPU, sim…
A new proposal calls for a common GPU execution and memory-management layer above CUDA, ROCm, and Intel XPU/oneAPI so that AI workloads are not tightly coupled to a single vendor, targeting 13B-class …
A calibrated one-hop graph reranker produced identical hit-at-five, MRR, and trusted evidence sets to graph-free retrieval across 250 frozen paired requests, with graph candidates appearing in only 5 …
Ketney Otto, a researcher and academic staff member at Lucian Blaga University of Sibiu in Romania, is requesting a cs.LG arXiv endorsement for a manuscript titled "Leakage-Aware Benchmarking of Machi…
Hugging Face users report that approval granted through Meta's official LLaMA application process at ai.meta.com does not automatically carry over to the corresponding gated repositories on Hugging Fa…
A Hugging Face user on a free account reported a 403 error stating "You've reached your CPU Basic quota limit across all your Spaces!" despite owning only one Space, aideveloperlol26/enterprise-ai-cop…