
MiniMax M2.7 is now in AdaL. What stood out to us was Agent Teams. Agents can take different roles, search tools, challenge each other’s reasoning, and work through complex coding tasks together. ~2.5% of Sonnet pricing. ~5% of Opus pricing
AdaL CLI
41 posts

@adalengineer
The new self-evolving coding agent girl in town!

MiniMax M2.7 is now in AdaL. What stood out to us was Agent Teams. Agents can take different roles, search tools, challenge each other’s reasoning, and work through complex coding tasks together. ~2.5% of Sonnet pricing. ~5% of Opus pricing


I packaged up the "autoresearch" project into a new self-contained minimal repo if people would like to play over the weekend. It's basically nanochat LLM training core stripped down to a single-GPU, one file version of ~630 lines of code, then: - the human iterates on the prompt (.md) - the AI agent iterates on the training code (.py) The goal is to engineer your agents to make the fastest research progress indefinitely and without any of your own involvement. In the image, every dot is a complete LLM training run that lasts exactly 5 minutes. The agent works in an autonomous loop on a git feature branch and accumulates git commits to the training script as it finds better settings (of lower validation loss by the end) of the neural network architecture, the optimizer, all the hyperparameters, etc. You can imagine comparing the research progress of different prompts, different agents, etc. github.com/karpathy/autor… Part code, part sci-fi, and a pinch of psychosis :)

@karpathy dropped autoresearch. so we ran AdaL @adalengineer vs Claude Code on his benchmark. AdaL won on both A10 and H100. same benchmark. same backbone model. better agent. the big difference: in long autonomous loops, AdaL keeps going, follows instructions better, and doesn’t stop early. repo: github.com/SylphAI-Inc/au…


Introducing GLM-5-Turbo: A high-speed variant of GLM-5, excellent in agent-driven environments such as OpenClaw. Coding Plan Max: z.ai/subscribe OpenRouter: openrouter.ai/z-ai/glm-5-tur… API: docs.z.ai/guides/llm/glm…



Builders 🚀 You can now experiment with GLM models inside AdaL CLI with free access. A coding agent designed for real developer workflows. • multi-model support • long-term memory • designed for shipping products faster Exactly the kind of tooling we want to support through the Z.ai Startup Program. Watch the video below.👇





We will be able to fix these three things!




introducing the AI Agent Glow Up ✨ Hackathon with @adalengineer ! a curated hackathon for technical builders in SF, with judges from: Gemini, NVIDIA, Meta, Pika, Exa AI, YC and more! 📷 7th March at @WorkOS offices! the focus: building beautiful UI/UX experiences for agents. hosted by @buildclub_ with: @Google, @WorkOS, @AgoraIO, @PrefectIO, @ExaAILabs and @gmi_cloud. many prizes ($15K+), street creds, photographers / headshots and more up for grabs. may the most cracked builder win! RSVP (spots are capped/vetted so get in fast) 📷🧵