Trending

Trained LLMs exclusively on pre-1913 texts

T5Gemma 2: The next generation of encoder-decoder models

Show HN: Learning a Language Using Only Words You Know

Launch HN: Pulse (YC S24) – Production-grade unstructured document extraction

Statistical Learning Theory and ChatGPT

Show HN: Paper2Any – Open tool to generate editable PPTs from research papers

Fluent: A Localization System for Natural-Sounding Translations

A school locked down after AI flagged a gun. It was a clarinet

Ditch the Chain-of-Thought Hacks: A Modular System for Composing AI Operations

Article: NextGen Search - Where AI Meets OpenSearch Through MCP

In this article, authors Srikanth Daggumalli and Arun Lakshmanan discuss next-generation context-aware conversational search using OpenSearch and AI agents powered by Large Language Models (LLMs) and Model Context Protocol (MCP). By Srikanth Daggumalli, Arun Lakshmanan

Transformers v5 Introduces a More Modular and Interoperable Core

Hugging Face has released the first candidate for Transformers v5, marking a significant evolution from v4 five years ago. The library has grown from a specialized model toolkit to a critical resource in AI development, achieving over three million installations daily and more than 1.2 billion total installs. By Robert Krzaczyński

Podcast: Building a More Appealing CLI for Agentic LLMs Based on Learnings from the Textual Framework

Will McGugan, the maker of Textual and Rich frameworks, speaks about the reasoning of developing the two two libraries and the lesson learned. Also, he shares light on Toad, his current project, which he envisions being a more visually appealing way of interacting with agentic LLMs through command line. By Will McGugan

What is something AI still struggles with, in your experience?

Listen... “Multilingual voice” support is fake!!!

Computational Creativity – Call for Papers for ICCC'26

Our AI sales agent has surprisingly brought in 29 new paying enterprise customers

[R] Semantic-Drive: Mining "Dark Data" in AV Logs via Neuro-Symbolic VLMs. Beating CLIP Recall by ~50% using "System 2" Inference-Time Verification (Code + Benchmark)

Fast on-device Speech-to-text for Home Assistant (open source)

AI Is Inventing Academic Papers That Don’t Exist — And They’re Being Cited in Real Journals

[D] AISTATS is Desk-Rejecting Papers Where Authors Accessed Reviewer Identities via the OpenReview Bug

TOP-70 AI Automations for Marketing and Content Creation

Xiaomi MiMo

Save item

MiMo-V2-Flash

Task: text-generation

Z.ai

Save item

GLM-TTS

Task: text-to-speech

Z.ai

Save item

GLM-ASR-Nano-2512

Task: automatic-speech-recognition

Nanbeige LLM Lab

Save item

Nanbeige4-3B-Thinking-2511

Task: text-generation

NousResearch

Save item

nomos-1

ByteDance

Save item

Dolphin-v2

Task: image-text-to-text

MaShijian

Save item

Qwen3-8B-Drama-Thinking

Task: text-generation

Jina AI

Save item

jina-vlm

Task: image-text-to-text

Kashif Salahuddin

Save item

SamKash-Tolstoy

Task: text-generation

microsoft

Save item

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

n3d1117

Save item

chatgpt-telegram-bot

🤖 A Telegram bot that integrates with OpenAI's official ChatGPT APIs to provide answers, written in Python

huggingface

Save item

text-generation-inference

Large Language Model Text Generation Inference

TransformerLensOrg

Save item

TransformerLens

A library for mechanistic interpretability of GPT-style language models

NoDataFound

Save item

hackGPT

I leverage OpenAI and ChatGPT to do hackerish things

ggerganov

Save item

whisper.cpp

Port of OpenAI's Whisper model in C/C++