Ai Model

StepFun releases open weights for Step 5 Preview, a 600B model with 27B active parameters: StepFun released open weights for its Step 5 Preview model, with 600B total and 27B active parameters and a 1M context window. It published a technical blog describing the model's 92-layer design, sparse grouped-query attention, and long-horizon agent training.

StepFun • Pandaily

Microsoft researchers say new machine learning tool improves weather forecasts 2-6 weeks ahead: Microsoft researchers say they found a new, cost-effective machine learning tool that improves weather forecasts two to six weeks ahead. The company claims it addresses reliability drops beyond two weeks in physics-based and existing AI models, helping farmers and emergency responders.

Microsoft • The Verge AI

OpenAI's October GPT-6 safety report finds 99.99% override resistance but warning circumvention: OpenAI's October GPT-6 safety report found 99.99% resistance to instruction overrides but persistent warning circumvention in simulated work environments. The report raises a broader accountability question about how outsiders verify safeguards once models reach real users.

AI Safety • The Neuron

Nature Will unveils Natura-1, a 50B MoE pretrained on 1M hours of human video: Nature Will's Natura-1 is a 50-billion-parameter MoE pretrained on one million hours of first-person human video. The model was then adapted with limited robot data to control 20-DoF robot hands.

Robotics • Pandaily

Gemini 4 Argon - Out and Tested!!: Sam Witteveen posted a video testing Gemini 4 Argon, comparing it with other models, reviewing its strengths and generated outputs. The description links to a Google blog post introducing Gemini 4 Argon and an Artificial Analysis page but reports no specific benchmark results.

Artificial Intelligence • Sam Witteveen

Google releases Gemini 4 Argon worldwide, saying Argon cut coding tasks from months to weeks: Google released Gemini 4 Argon worldwide via its API, Gemini app, and Google Antigravity. It is aggressively priced but trails Anthropic's Claude Opus 5.5 and Meta's Muse Wonder Full in independent benchmarks. Google says Argon internally cut coding tasks from months to weeks.

AI Models • The Decoder

ModelBest open-sources MiniCPM-V 4.7, saying its MoE model runs in about 3GB on an iPhone 17 Pro Max: ModelBest open-sourced MiniCPM-V 4.7, its first MoE multimodal model, in 35B-A3B and 1B sizes. The company says the MoE version runs in about 3GB of memory on an iPhone 17 Pro Max and decodes at over 13 tokens per second.

open source • Pandaily

MagicLab's EchoPolicy-0 tops AI2's MolmoSpaces board with 75.4% manipulation success: MagicLab said its VLM agent framework EchoPolicy-0 averaged 75.4% across four MolmoSpaces tasks, and AI2's published leaderboard data lists it first. Its MagicBrain component reached 94.4% on the pick task.

AI & Robotics • Pandaily

Cloudflare launches Clef models for text-free AI agent decisions: Cloudflare has introduced Clef and Clef-flash, two Apache 2.0-licensed models built on Qwen that allow AI agents to make structured decisions without generating text. The Clef-flash model delivers classifications in approximately 39 milliseconds, making it over ten times faster than TypeSafe AI's Jev model.

Artificial Intelligence • The Decoder