Models & Labs
GPT-5.6 Luna Price Cut by 80%
Lev Selectorhigh confidence
Why it matters
- →Makes advanced AI more accessible due to lower costs
- →Demonstrates the effectiveness of recursive self-improvement
- →Encourages wider adoption of AI technologies
OpenAI has announced an 80% price reduction for its GPT-5.6 Luna model. This move is part of a broader trend of recursive self-improvement (RSI) where AI models are used to optimize their own performance and cost efficiency. The price cut allows tasks to be solved for approximately 7 cents, compared to the previous cost, making advanced AI capabilities more accessible.
Read originalMore from Lev Selector
© Lev SelectorModels & Labsmodels
DeepSeek V4 Flash Released
DeepSeek has released version 4 of its Flash model, offering improved performance and capabilities.
Lev Selector
© Lev SelectorModels & Labsmodels
Anthropic Removes 80% of Claude Code Prompts
Anthropic has streamlined its Claude Code by removing 80% of internal prompts to improve model performance.
Lev Selector
© Lev SelectorVideo & Creative AIimage
Microsoft Launches Mage-Flow Text-to-Image
Microsoft has introduced Mage-Flow, a new text-to-image model, enhancing creative AI capabilities.
Lev Selector
More in Models & Labs
Models & Labsmodels
Llama.cpp b10208 Release Enhances SYCL Performance
The latest b10208 release of llama.cpp introduces significant improvements in SYCL performance, particularly with the addition of oneMKL GEMM flash attention for XMX-accelerated prompt processing. This update addresses previous issues with interleaved destination layouts in the normalize kernel, ensuring more accurate attention outputs across models. By removing redundant stream waits and refining MKL FA dispatch gates, the release optimizes processing speeds, nearly doubling performance in some cases. These enhancements make llama.cpp a more robust and efficient tool for developers working with large language models.
llama.cpp Releases
Models & Labsmodels
llama.cpp b10211 Release Expands Platform Support
The latest b10211 release of llama.cpp continues its trend of broadening platform compatibility, making it a versatile tool for developers across various systems. Notably, this update includes support for Ubuntu with ROCm 7.2, enhancing performance for AMD GPU users. Windows users benefit from the inclusion of CUDA 12 and 13 DLLs, ensuring compatibility with the latest NVIDIA technologies. While the release doesn't introduce new model architectures, it solidifies llama.cpp's position as a flexible inference runtime across diverse hardware configurations.
llama.cpp Releases
Models & Labsmodels
llama.cpp b10212 Release Optimizes MTP Tensor Loading
The b10212 release of llama.cpp brings a significant efficiency boost by ensuring MTP tensors are loaded only when necessary. This optimization, co-authored by Stanisław Szymczyk, targets models that support MTP, reducing unnecessary resource usage. The update is applicable across environments like macOS, Linux, Windows, and openEuler, making it widely relevant. While there are no new models or architectures introduced, the focus on performance and resource management makes llama.cpp more effective for developers. This release quietly enhances the runtime experience, particularly for those leveraging MTP-supported models.
llama.cpp Releases