[⋯]Loading

Built solo in Lille, FR·v0.6

Dev & AI feed

The best of dev and AI, scored every day by an agent. Filtered, summarized, ranked. No color, no noise — just the substance.

Issue: No. 138
Date: MAY 18, 2026
Edition: EN · DAILY
Sources: 14 active
Articles: 35 today

§ Feed·Vol. 02·No. 138

Last ingest·08:00 UTC+0·Next·08:00

Filters

Reference PanelA.1

01. Type— 5

02. Period— 3

03. Source— 7

04. Score— min.

0 active

$⌘K

Articles / day35

7-day avg.52

Mon → Sun-91%

Feed · 822 articles

sort byscore·DESC ↓

581AUG 1214:52

articleHuggingFace Blog·9 mo. ago

Neural Super Sampling is here!

Neural Super Sampling (NSS) is Arm's real-time upscaling model for mobile GPUs with Neural Accelerators, enabling high‑resolution rendering at lower compute cost for mobile gaming and XR. A demo shows a 50% GPU workload reduction, upscaling from 540p to 1080p in 4 ms, with NSS integrated into Unreal Engine via plugins and Vulkan ML extensions; supporting resources include a technical blog, a white paper, and quickstart guides.

★★★★★·HuggingFace Blog

582AUG 1200:00

articleHuggingFace Blog·9 mo. ago

FilBench - Can LLMs Understand and Generate Filipino?

FilBench is a comprehensive evaluation suite to assess LLM capabilities for Tagalog, Filipino, and Cebuano, focusing on fluency, linguistic tasks, translation, and cultural knowledge. It organizes tasks into four categories (Cultural Knowledge, Classical NLP, Reading Comprehension, Generation) and reports a FilBench Score across 20+ models.

★★★★★·HuggingFace Blog

583AUG 1200:00

articleHuggingFace Blog·9 mo. ago

TextQuests: How Good are LLMs at Text-Based Video Games?

TextQuests introduces a benchmark to evaluate LLM-based agents in text-based interactive games, emphasizing long-context reasoning and learning through exploration. It uses 25 classic Infocom games with two modes (With Clues / No Clues) and measures Game Progress and Harm over up to 500 steps, preserving full history for long-context evaluation.

★★★★★·HuggingFace Blog

584AUG 0800:00

articleHuggingFace Blog·9 mo. ago

Accelerate ND-Parallel: A guide to Efficient Multi-GPU Training

Accelerate ND-Parallel guides how to combine multiple parallelism strategies (data, fully sharded data, tensor, context) for multi-GPU training. It provides concrete config examples (dp_shard_size, dp_replicate_size, cp_size, tp_size) and an FSDP plugin, plus Axolotl integration and end-to-end training scripts to minimize inter-device communication at scale. The article also discusses how to compose strategies for large models and points to ready configs and docs.

★★★★★·HuggingFace Blog

585AUG 0800:00

toolHuggingFace Blog·9 mo. ago

Introducing AI Sheets: a tool to work with datasets using open AI models!

AI Sheets is a no-code tool for building, transforming, and enriching datasets with open AI models, deployable locally or on the Hugging Face Hub. It uses a spreadsheet-like UI where prompts generate new columns, and you can validate or edit cells to fine-tune prompts with few-shot examples. It supports comparing models, data cleaning, classification, enrichment, and synthetic data generation.

★★★★★·HuggingFace Blog

586AUG 0700:00

articleHuggingFace Blog·9 mo. ago

Vision Language Model Alignment in TRL

TRL expands Vision Language Model alignment with Mixed Preference Optimization (MPO), Group Relative Policy Optimization (GRPO), and Group Sequence Policy Optimization (GSPO), extending beyond pairwise DPO to richer signals. It also adds Reinforce Leave One Out (RLOO) and Online DPO for scalable multimodal alignment, plus native SFT support and reproducible training scripts.

★★★★★·HuggingFace Blog

587AUG 0500:00

articleHuggingFace Blog·10 mo. ago

Welcome GPT OSS, the new open-source model family from OpenAI!

OpenAI releases GPT OSS, an open-weight family with 117B and 21B MoE models using 4-bit MXFP4 quantization for fast inference and low resource use. The 120B fits on an 80GB GPU and the 20B on 16GB, both Apache-2.0 licensed; usable via Hugging Face Inference Providers for local or on-device deployments.

★★★★★·HuggingFace Blog

588AUG 0419:51

articleHuggingFace Blog·10 mo. ago

Measuring Open-Source Llama Nemotron Models on DeepResearch Bench

AI-Q combines Llama 3.3-70B Instruct and Llama-3.3-Nemotron-Super-49B-v1.5 to enable long-context retrieval, agentic reasoning, and tool use in open-source stacks. NVIDIA details model lineage, post-training, and transparent evaluation metrics (hallucination detection, multi-source synthesis, citation trust, RAGAS), plus a 49B Nemotron running on a single H100. DeepResearch Bench ranks AI-Q top among fully open stacks with a score of 40.52 in LLM with Search (Aug 2025).

★★★★★·HuggingFace Blog

589AUG 0114:25

articleHuggingFace Blog·10 mo. ago

3LM: A Benchmark for Arabic LLMs in STEM and Code

3LM est un benchmark multidomaine pour évaluer les LLM arabes en STEM et en code, déployant trois jeux de données (Native STEM MCQs, Synthetic STEM et Arabic Code Benchmarks) et des métriques comme pass@1 via EvalPlus. Le pipeline combine OCR, génération par LLM et vérifications humaines, et propose l'accès aux jeux sur HuggingFace et le code sur GitHub.

★★★★★·HuggingFace Blog

590JUL 3100:00

articleHuggingFace Blog·10 mo. ago

Implementing MCP Servers in Python: An AI Shopping Assistant with Gradio

The article demonstrates how to implement an MCP server with Gradio to plug an LLM into Hugging Face models. It covers automatic conversion of Python functions into MCP tools, real-time progress notifications, and automatic file uploads, illustrated by an AI shopping assistant using IDM-VTON for virtual try-on.

★★★★★·HuggingFace Blog

591JUL 2900:00

articleHuggingFace Blog·10 mo. ago

Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face

Trackio est une bibliothèque légère d’expérimentation open-source qui remplace wandb et offre un tableau de bord local Gradio, avec synchronisation vers Hugging Face Spaces pour partager les métriques. Elle vise simplicité, traçabilité des métriques et énergie GPU via nvidia-smi, et peut être utilisée comme drop-in wandb.

★★★★★·HuggingFace Blog

592JUL 2500:00

toolHuggingFace Blog·10 mo. ago

Say hello to `hf`: a faster, friendlier Hugging Face CLI

HF renames the Hugging Face CLI from huggingface-cli to hf to reorganize commands around a clear hf <resource> <action> pattern, improving ergonomics and discoverability. The migration keeps the legacy CLI functional with warnings and documents how to install (pip install -U huggingface_hub) and verify (hf version) and explore commands (hf --help). It also introduces the hf jobs service to run scripts or Docker images on HF infrastructure with pay-as-you-go billing.

★★★★★·HuggingFace Blog

593JUL 2500:00

articleHuggingFace Blog·10 mo. ago

Parquet Content-Defined Chunking

Parquet Content-Defined Chunking (CDC) is now available in PyArrow and Pandas, enabling deduplication of Parquet files on Hugging Face’s Xet storage layer. CDC reduces data transfer and storage costs by uploading or downloading only changed data chunks. The article shows how to enable CDC with use_content_defined_chunking and outlines several deduplication scenarios with code examples.

★★★★★·HuggingFace Blog

594JUL 2300:00

articleHuggingFace Blog·10 mo. ago

TimeScope: How Long Can Your Video Large Multimodal Model Go?

TimeScope is an open-source benchmark that tests long-video understanding by inserting short needle clips into base videos (1 min to 8 hours). It evaluates localized retrieval, information synthesis, and fine-grained temporal perception, revealing that many SOTA models struggle with true temporal comprehension.

★★★★★·HuggingFace Blog

595JUL 2300:00

articleHuggingFace Blog·10 mo. ago

Fast LoRA inference for Flux with Diffusers and PEFT

LoRA adapters enable customizing diffusion models but can slow or complicate inference. This post shows how to speed up LoRA inference for Flux using a recipe based on FA3, FP8 quantization, and torch.compile, while staying hot-swapping–ready. It includes a concise code example that applies quantization, sets the attn processor, and compiles the transformer for faster inference.

★★★★★·HuggingFace Blog

596JUL 2118:01

articleHuggingFace Blog·10 mo. ago

Accelerate a World of LLMs on Hugging Face with NVIDIA NIM

NVIDIA NIM offre un conteneur unique pour deployer rapidement une large gamme de LLM via Hugging Face, en automatisant l’adaptation, l’analyse du modele et le choix du backend (TensorRT-LLM, vLLM, SGLang). Il prend en charge Hugging Face, GGUF et TensorRT-LLM et illustre le deployment avec Codestral-22B via une commande Docker et tokens API.

★★★★★·HuggingFace Blog

597JUL 1800:00

articleHuggingFace Blog·10 mo. ago

Arc Virtual Cell Challenge: A Primer

Arc Institute lance le Virtual Cell Challenge, qui vise à entraîner un modèle capable de prédire l’effet du silençage d’un gène sur une cellule, même dans des types cellulaires inédits (contexte généralisation). Le jeu de données réunit environ 300k profils RNA‑seq d’une cellule unique et propose un cadre mathématique pour séparer le signal du perturbation, l’hétérogénéité et le bruit technique, avec des architectures comme le State Transition Model et le State Embedding Model.

★★★★★·HuggingFace Blog

598JUL 1700:00

articleHuggingFace Blog·10 mo. ago

Back to The Future: Evaluating AI Agents on Predicting Future Events

AI evaluation should shift from recalling facts to forecasting future events. FutureBench uses real-world prediction markets and live news to test agents' ability to reason under uncertainty and synthesize information to predict outcomes.

★★★★★·HuggingFace Blog

599JUL 1700:00

mcpHuggingFace Blog·10 mo. ago

Five Big Improvements to Gradio MCP Servers

Gradio has released version 5.38.0 to enhance MCP servers with Seamless Local File Support via a new File Upload endpoint, real-time progress streaming for MCP clients, and a one-line OpenAPI-to-MCP conversion using gr.load_openapi. The update also improves authentication by allowing server arguments to be declared as gr.Header and surfaced in docs.

★★★★★·HuggingFace Blog

600JUL 1700:00

articleHuggingFace Blog·10 mo. ago

Consilium: When Multiple LLMs Collaborate

Consilium est une plateforme qui fait débattre et faire consensus entre plusieurs LLMs via des discussions structurées, avec des modes comme consensus, vote majoritaire ou classement par choix. Déployée comme interface Gradio et serveur MCP, elle visualise une table ronde et les échanges des experts. L'article relie l'idée au MAI-DxO de Microsoft pour démontrer l'efficacité du multi-LLM.

★★★★★·HuggingFace Blog

Page 30 / 42

← Prev.Next →

20 of 822 shown

Issue 138 · Digest

The weekly digest, every Sunday.

20 articles ranked by an agent. No noise, no ads. One-click unsubscribe.

Subscribe →

[top 7 days]B.1

01.
I turned a $80 RK3562 Android tablet into a Debian Linux workstation
Hacker News (100+ pts)
02.
Mullvad exit IPs as a fingerprinting vector
Lobsters
03.
Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality
HuggingFace Blog
04.
what 262,715 regex questions on stack overflow haven't answered
Lobsters
05.
int a = 5; a = a++ + ++a; a = ? (2011)
Lobsters

Colophon · MakerC.1

Quentin Lecocq · @celdama

Fullstack dev · CRO freelance · Lille, FR

Lantern is a side-project — aggregation, AI scoring, weekly digest. Built with Next.js 16, Drizzle, Neon & Claude. One maintainer.

[X][GitHub][RSS][Site]

ShortcutsC.2

Search⌘ K
Next articleJ
Previous articleK
OpenEnter
FavoriteF

Dev & AI feed

§Feed · 822 articles

Feed · 822 articles