Trending

Real-time action chunking with large models

MiniMax-M1 open-weight, large-scale hybrid-attention reasoning model

Show HN: Trieve CLI – Terminal-based LLM agent loop with search tool for PDFs

Building Effective AI Agents

LLMs pose an interesting problem for DSL designers

Show HN: Cpdown – Copy any webpage/YouTube subtitle as clean Markdown(LLM-ready)

Snorting the AGI with Claude Code

Breaking Quadratic Barriers: A Non-Attention LLM for Ultra-Long Context Horizons

Show HN: Trieve CLI – Terminal-Based LLM Agent Loop with Search Tool for PDFs

what i learned from building 50+ AI Agents last year

We built this project to increase LLM throughput by 3x. Now it has been adopted by IBM in their LLM serving stack!

Anyone else slowly replacing Google with ChatGPT for everyday thinking?

[D] 500+ Case Studies of Machine Learning and LLM System Design

[D] What tasks don’t you trust zero-shot LLMs to handle reliably?

Is this a good use case of an agent

[R] Towards Universal Semantics with Large Language Models

Can your favourite local model solve this?

Build AI Agents for Free with Self-Hosted LLMs and Skip Those Cloud Bills!

MiniMax

Save item

MiniMax-M1-80k

Task: text-generation

Menlo Research

Save item

Jan-nano

Task: text-generation

Moonshot AI

Save item

Kimi-Dev-72B

Mistral AI_

Save item

Magistral-Small-2506

MiniMax

Save item

MiniMax-M1-40k

Task: text-generation

inclusionAI

Save item

Ming-Lite-Omni

Menlo Research

Save item

Jan-nano-gguf

Task: text-generation

OpenBMB

Save item

MiniCPM4-8B

Task: text-generation

Qwen

Save item

Qwen3-Embedding-0.6B

Task: text-generation