Articoli

Munder Difflin — Agent harness to run an office of your clones

Error by AI scribe during medical appointment leaves patient devastated

Everyone is building LLM routers, we deprecated ours

Kimi K3 Architecture Notes

Nativ — Run AI locally on your Mac

How LLMs Actually Work | 0xkato

Introducing Gemma 4 12B

Introducing Unsloth Studio | Unsloth Documentation

Bring Your Agent to Teams | Teams SDK

Emotion Concepts and their Function in a Large Language Model

Nicholas Carlini - Black-hat LLMs | [un]prompted 2026 - YouTube

Qwen

Introducing Claude Opus 4.7 Anthropic

PrismML — Concentrating intelligence

Vibe Coding per Aziende: Come Usare l'AI per lo Sviluppo Software Senza Rischi

AI in anestesia: come KOI riduce gli errori di classificazione ASA-PS dell'89%

GDPR e Intelligenza Artificiale: Guida Pratica per Aziende Europee

Come scegliere un'infrastruttura AI privata per la tua azienda

Introducing Mistral Small 4 | Mistral AI

Coding my Handwriting — Amy Goodchild

On-Premise vs Cloud AI: Quale Scegliere per la Tua PMI — Analisi Completa

Natural Language to SQL: interrogare i database aziendali senza scrivere codice

My chief of SEO, Claude Cowork

spent the entire day testing Qwopus (Claude 4

GitHub - z-lab/paroquant: [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference

I packaged up the 'autoresearch' project into a new self-contained minimal repo if people would like to play over the weekend

building an autonomous company

Agent Safehouse

Introduction to LLM Post-Training Techniques | PDF

Distillation Training : 4 Bits

I've been thinking a bit about continual learning recently, especially as it relates to long-running agents (and running a few toy experiments with MLX)

AI per Studi Professionali: Guida GDPR Completa + 15 Casi d'Uso Concreti

The Best OpenClaw Alternatives 2026 – from N… – Till Freitag

AI Act 2026: guida pratica per le PMI europee

microgpt

GLM-5

Costo dell'AI per PMI: Breakdown Completo dei Costi e Calcolatore ROI

Step 3.5 Flash: Fast Enough to Think. Reliable Enough to Act.

ORCA vs ChatGPT: perché il tuo chatbot aziendale deve essere privato

Keycloak

Alternativa a ChatGPT per Aziende: Confronto Completo GDPR, Costi e Sicurezza

Perché la tua azienda ha bisogno di AI privata (e non di ChatGPT)

Come Implementare AI in Azienda: La Roadmap Completa da Zero a Produzione

moonshotai/Kimi-K2.5 · Hugging Face

Welcome - Poke Documentation

NVIDIA PersonaPlex: Natural Conversational AI With Any Role and Voice - NVIDIA ADLR

Unrolling the Codex agent loop

AI Privata per PMI: La Guida Completa 2026 per Imprese Europee

Recursive Language Models | Alex L. Zhang

Recursive Language Models: the paradigm of 2026

The Art of Context Windows: Our AI Had Alzheimer's: Here's How We Taught It To Remember

Il Disclaimer muore.

ToolOrchestra

OpenCode | The open source AI coding agent

You Should Write An Agent · The Fly Blog

Getting Started - SWE-agent documentation

How to Build an Agent - Amp

SAM Audio

We Got Claude to Fine-Tune an Open Source LLM

Use Claude Code with Chrome (beta) - Claude Code Docs

LLMRouter - LLMRouter

Everything as Code: How We Manage Our Company In One Monorepo | Kasava

Introduction | MCP Toolbox for Databases

Effective harnesses for long-running agents Anthropic

AI Explained - Stanford Research Paper.pdf - Google Drive

We present Olmo 3, our next family of fully open, leading language models

A2UI

Nano Banana Pro is making millions of interior designers obsolete I upload my floor plan and it design the whole house for me, and even generate real images for each room based on the dimension

How to Segment Videos with Segment Anything 3 (SAM3)

Introducing MagicPath, an infinite canvas to create, refine, and explore with AI

Nano Banana Pro is wild

Next up… Slide Decks! Turn your sources into a detailed deck for reading OR a set of presentation-ready slides

Presentations — Benedict Evans

Nano Banana Pro: Gemini 3 Pro Image model from Google DeepMind

Google Antigravity

GitHub Projects Community (@GithubProjects) on X

I’m starting to get into a habit of reading everything (blogs, articles, book chapters,…) with LLMs

Love this framing！ This is exactly what we’re building at Weco: - you write an eval script (your verifier) - Weco iterates on the code to optimize it against that eval Software 1

Supercharge your OCR Pipelines with Open Models

[2511.09030] Solving a Million-Step LLM Task with Zero Errors

Gemini 3: Introducing the latest Gemini AI model from Google

[2511.10395] AgentEvolver: Towards Efficient Self-Evolving Agent System

Use Cases | Claude

Improving frontend design through Skills | Claude

said we should delete tokenizers

You Should Write An Agent · The Fly Blog

"🚀 Hello, Kimi K2 Thinking! The Open-Source Thinking Agent Model is here"

Link to the Strix GitHub repo: (don't forget to star 🌟)

Source: Thanks and Bharat for showing the world you can in fact tra...

This Claude Code prompt literally turns Claude Code into ultrathink...

Tongyi DeepResearch: A New Era of Open-Source AI Researchers | Tongyi DeepResearch

AI Act Single Information Platform | AI Act Service Desk

eurollm.io

Introducing Mistral AI Studio. | Mistral AI

OpenSnowcat - Enterprise-grade behavioral data platform.

Dr Milan Milanović (@milan_milanovic) on X

I quite like the new DeepSeek-OCR paper

olmOCR 2: Unit test rewards for document OCR | Ai2

We used DeepSeek OCR to extract every dataset from tables/charts ac...

Scripts I wrote that I use all the time