VibeThinker-3B: A 3B Dense Reasoning Model Built on Qwen2.5-Coder-3B With the Spectrum-to-Signal Post-Training Pipeline
While recent breakthroughs in AI reasoning have largely been driven by massive scale, pouring in billions of parameters to cross complex cognitive thresholds—VibeThinker-3B is charting a completely different path. Created by researchers from Sina Weibo Inc (China), this 3-billion-parameter model proves that efficiency can punch far above its weight class. Released under an open-source MIT license, VibeThinker-3B matches the performance of models hundreds of times its size on verifiable tasks
A small AI model with 3 billion parameters, built on an existing coder model and trained with a technique called the Spectrum-to-Signal pipeline, achieves reasoning performance comparable to models hundreds of times larger on verifiable tasks like mathematics and coding. The model is designed as a specialist for problems where answers can be checked, rather than a general-knowledge system, and runs efficiently on standard hardware. It matters because it demonstrates that reasoning capability does not require massive scale, potentially making advanced reasoning accessible for cost-sensitive deployments and edge devices. The model uses supervised fine-tuning to explore multiple solution paths, reinforcement learning to strengthen correct ones, and can further improve answers at test time by having itself verify intermediate claims without adding parameters.
One short email a day with the stories that matter. Free. Unsubscribe with one click.
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on Maven
Anthropic releases new Mythos and Fable models amid RSI concerns
Anthropic says the new models "show improvements in areas like coding, reasoning, and vision," as well as in communicating more clearly with users.
Also reported by The Verge, SiliconANGLE and MarkTechPost
Runway’s Praxis-1 world action model for robotics is now available
Praxis-1 builds on Runway’s work as a founding member of the Cosmos Coalition, advancing open world models for physical AI. | Source: Runway Runway AI Inc. yesterday released Praxis-1, its world action model for robotics. The model is now available to developers with open weights under the Apache 2.0 license. Runway first announced Praxis-1 in September with launch partners including Noble Machines, Standard Bots, and Ultra. Since then, these companies have been running the model on their own ha
Google releases Gemini 4 Carbon with agent ‘swarm’ feature
Google is rolling out its latest AI model, Gemini 4 Carbon, to the general public after releasing it to a select group of "cybersecurity defenders" two weeks ago. Google claims Carbon is its "strongest model" yet, and capable of competing with the very best systems from Anthropic and OpenAI. Google says Gemini 4 Carbon "pushes the frontier even further" than Argon, referring to the company's other frontier model that launched only last month. The company said Argon will likely
Gemini 4 Carbon is now available
The latest version aims to deliver improved performance while reducing the computational resources and energy required for AI operations.
Google Launches Gemini Decisions API With Gemini Decision 1 at $0.10/M Tokens
Google has launched the Gemini Decisions API, powered by a new model, Gemini Decision 1 (gemini-decision-1). The Gemini Decisions API does not generate text. It scores up to 1,000 typed questions against one shared input and returns calibrated probabilities. For developers, this targets the small branching calls inside agents: routing, policy checks, tool selection and grading. Google prices it at $0.10 per 1M input tokens, with zero output tokens billed. TL;DR Size: Context is 262,144 t
Also reported by SiliconANGLE
Introducing AlphaProof Code: a breakthrough in verifying complex software at depth
AlphaProof Code agents wrote three million lines of proofs in Lean to verify Signal’s core encryption.