GameCraft-Bench evaluates whether large language models can build playable games end-to-end using a real game engine. The benchmark includes assessments of major models like Opus-4.7 and GPT-5.5, with interest in how medium-sized models (e.g., 30-70B parameters) perform on game development tasks.
Gemma 4 E2B achieves 255 tokens per second in-browser on an M4 Max using WebGPU kernels. The demo and kernels are now available on Hugging Face for public use.
In 2025, the economics of code production shifted dramatically, making code generation effectively free and instant. This change caused a cultural shift in software development, where lines of code moved from being carefully curated to being disposable and regenerable.
Users report that the Web UI is missing in the latest llama.cpp version b9680, while version b9664 functions correctly. The issue was reported in a GitHub issue and confirmed via Docker usage.
LLaMA.cpp release b9684 introduces a new 3D convolution operation (conv_3d) and includes optimized implementations. The release provides prebuilt binaries for macOS, Linux, Android, Windows, and openEuler across various architectures and hardware acceleration options, including SYCL, Vulkan, CUDA, and OpenVINO.
A new Rust-based framework enables small language models to achieve performance comparable to larger models, using efficient memory management and optimized computation. The approach reduces resource demands without sacrificing accuracy, making advanced AI accessible to resource-constrained environments.
TRELLIS.2 has been ported to run natively on MLX for Apple Silicon. The model supports 512x512 and 1024x1024 image inputs, with generation times of approximately 70 seconds for 512x517 and 300 to 700 seconds for 1024x1024 on an M4 Max with 128GB unified memory.
A user asks whether running GLM-5.2 on four Ascend GX10 chips (DGX Sparks) is feasible. They inquire about 4-bit quantization using 512GB unified memory and estimate prompt and output token speeds for 100k context length, noting no existing performance data is available online.
The author outlines three core goals: clarifying frontier AI model evolution, building an open AI ecosystem, and creating institutions to support these missions. Interconnects serves as a raw, independent voice for frontier AI thinking, with a dedicated technical audience of over 70K subscribers. The blog maintains paywalled comments to prevent AI-generated noise, and the author plans to reach 1000 paid subscribers by summer, emphasizing financial sustainability and independence amid rising AI service costs.
llama.cpp version b9682 introduces Vulkan support for Linux and Windows, enabling GPU acceleration. The release includes binaries for macOS, Linux, Android, Windows, and openEuler across multiple architectures, with CPU and GPU options including CUDA, OpenVINO, SYCL, and ROCm.
GLM-5.2, with 753B parameters and a 1M-token context window, is now accessible on local hardware through quantization. Its MIT license and extensive training data enable community fine-tuning of smaller models, promising significant improvements for local AI setups.
A local 30B agent, using headless screenshot loops, autonomously debugs a raytraced FPS demo in pure C by capturing frames at key events and iterating on fixes. The agent builds a recursive visual debugging loop, demonstrating that simple feedback mechanisms can enable small models to solve complex, visually grounded tasks.
The SIQ-1 model, trained using PPO with verifiable reward, outperforms GLM-5.2 and Qwen-350B on parameter-golf tasks, with outputs resembling Opus4.8. It also beats NEX and GPT-5.5 on the bullshit-bench test. The model and GGUF version are available on Hugging Face, along with a ZeroGPU-compatible agent demo.
The developer released a local LLM-powered RPG where NPCs, locations, items, and quests are generated as persistent in-game objects. These elements can be revisited and interacted with, and the game integrates LLMs into core RPG mechanics like dialogue, narration, and quest progression, while managing inventory, combat, and saves. The game sold about 1,800 copies in its first week and has a 4.0 store rating, indicating player interest in AI-driven RPG experiences.
LLaMA.cpp release b9678 includes optimization of mul_mat_f16_f32_l4 for decode and introduces new builds for macOS, Linux, Android, Windows, and openEuler. The release offers CPU, Vulkan, ROCm, OpenVINO, SYCL, and HIP support across multiple architectures, with a dedicated UI package available.
llama.cpp version b9677 updates logging to enforce max_capacity and removes queue expansion logic. The release includes binaries for macOS, Linux, Android, Windows, and openEuler across multiple architectures and hardware acceleration options, including Vulkan, CUDA, OpenVINO, and SYCL.
A user asks whether the 'needle in haystack' benchmark—used to evaluate model performance—is still relevant or has been abandoned. The post reflects on its historical use in model releases and questions if it is now considered outdated or forgotten.
LLaMA.cpp version b9674 fixes a use-after-free bug in SYCL's async memcpy during MoE prefill. The release includes binaries for macOS, Linux, Android, Windows, and openEuler, supporting CPU, Vulkan, ROCm, OpenVINO, SYCL, and CUDA across multiple architectures.
llama.cpp version b9675 enables FP16 support for operations like SQR, SQRT, LOG, SIN, COS, and CLAMP. The release includes binaries for macOS, Linux, Android, Windows, and openEuler across multiple architectures, with support for Vulkan, ROCm, OpenVINO, SYCL (FP16 and FP32), and CUDA 12.4 and 13.3.
The release of GLM 5.2 suggests open-weight models have caught up to Opus 4.8. Users are asking how long it will take to see open-weight models matching Mythos or Fable class performance from China.