MiniMax M2.7
Self-evolving AI model powering autonomous agents
In plain words
MiniMax M2.7 is a self-evolving AI model designed for developers and teams building AI-native workflows. It can create agent harnesses, coordinate multiple agents, and handle complex tasks including coding, debugging, and research. The model continuously learns and adapts to execute sophisticated work with minimal human supervision. It's available through an API and MiniMax Agent platform for builders working with autonomous systems.
written from the facts on this page · September 2026
From the sources
MiniMax M2.7 is a self-evolving AI model that helped build its own capabilities. It can create agent harnesses, collaborate via Agent Teams, and handle complex tasks like coding, debugging, and research. With strong SWE-Pro performance and reduced intervention time, it moves beyond static AI into systems that continuously learn, adapt, and execute complex work with minimal human input. Available via API and MiniMax Agent for builders pushing AI-native workflows.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
