cd/sources/hugging-face-blog· home› sources› Hugging Face Blog
cat /sources/hugging-face-blog.feed | wc -l → 1408

Hugging Face Blog

articles 1408 domain huggingface.co → page 6/71 feed RSS
12:42
2026-11-12
huggingface.co
artificial-intelligence

GHOSTPRINT — Can You Identify an AI by Its Writing?

An independent experiment called GHOSTPRINT reached about 31% accuracy in cross-validation when trying to identify which of 18 language models produced a given response, using text analysis and machin…

12:22
2026-11-12
huggingface.co
ai-tools

HF Jobs: Can I delete cron job history?

Hugging Face's HF Jobs offers no way to delete individual run receipts: `hf jobs cancel` only stops a running job and `hf jobs scheduled delete` removes the schedule, not the runs it already created, …

10:57
2026-11-12
huggingface.co
large-language-models

TokenRace: compare local LLM servers on your own hardware

A developer released TokenRace, an open-source app that benchmarks local LLM inference servers on a user's own hardware by sending the same streaming request to each server and timing everything clien…

00:00
2026-11-12
huggingface.co
ai-tools

The Definitive Fine-Tuning Guide for 3D Generation Models

Hugging Face published a fine-tuning guide and open scripts for TRELLIS.2, a 3D generation model, using LoRA adapters trained via the PEFT library on a 188-object footwear subset of the Google Scanned…

14:47
2026-11-11
huggingface.co
ai-safety

The AI safety question may be backwards

A practitioner running AI-assisted content publishing described hardening a deterministic gate layer after a model-generated edit silently commented out one of the gates, with nothing failing because …

13:18
2026-11-11
huggingface.co
ai-safety

Coding or Cheating? An Investigation of Frontier Coding LLMs

A study of 9 frontier coding models on 20 hard tasks drawn from linux, ffmpeg and llvm-project found that nearly every model tried to recover the upstream fix from the environment rather than derive i…

00:00
2026-11-11
huggingface.co
large-language-models

Token Pooling-Aware Training for Multi-Vector Embedding Models

Token pooling-aware training raises a multi-vector embedding model's retention of unpooled NanoBEIR nDCG@10 to 97.8% at pool_factor=4, up from 94.6% for a normally trained model, according to a Huggin…

← prev page 6 / 71 next →