Trending

Karpathy on DeepSeek-OCR paper: Are pixels better inputs to LLMs than text?

The security paradox of local LLMs

How do LLM's trade off lives between different categories?

A Brain-like LLM to replace Transformers

LLMs Can Get "Brain Rot"

Neural audio codecs: how to get audio into LLMs

Chezmoi introduces ban on LLM-generated contributions

ChatGPT Atlas

Binary Retrieval-Augmented Reward Mitigates Hallucinations

Australian-made LLM beats OpenAI and Google at legal retrieval

Qwen team is helping llama.cpp again

Teaching Your LLM to Tell Time: A Practical Guide to LLM Tool Integration

[R] rBridge: Predicting LLM Reasoning Performance with Small Proxy Models (100× Compute Reduction)

Agent that lets you prompt agents into existence?

[D] Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation

Researchers find LLMs can get "brain rot" from scrolling junk content online, just like humans

Qwen3-VL-2B and Qwen3-VL-32B Released

Qwen3-Next 80B-A3B llama.cpp implementation with CUDA support half-working already (up to 40k context only), also Instruct GGUFs

Liquid AI

Save item

LFM2-8B-A1B

Task: text-generation

AI21

Save item

AI21-Jamba-Reasoning-3B

Task: text-generation

IBM Granite

Save item

granite-4.0-h-small

Task: text-generation

IBM Granite

Save item

granite-4.0-micro

Task: text-generation

Liquid AI

Save item

LFM2-8B-A1B-GGUF

Task: text-generation

moondream

Save item

moondream3-preview

Task: text-generation

Qwen

Save item

Qwen3-VL-30B-A3B-Thinking

IBM Granite

Save item

granite-4.0-h-tiny

Task: text-generation

IBM Granite

Save item

granite-4.0-h-micro

Task: text-generation

openai

Save item

openai-cookbook

Examples and guides for using the OpenAI API

langchain-ai

Save item

langchain

🦜🔗 Build context-aware reasoning applications

pathwaycom

Save item

pathway

Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG.

run-llama

Save item

llama_index

LlamaIndex is the leading framework for building LLM-powered agents over your data.

NVIDIA

Save item

Megatron-LM

Ongoing research training transformer models at scale

EleutherAI

Save item

lm-evaluation-harness

A framework for few-shot evaluation of language models.

activepieces

Save item

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

f

Save item

awesome-chatgpt-prompts

This repo includes ChatGPT prompt curation to use ChatGPT and other LLM tools better.

khoj-ai

Save item

khoj

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.