SlimeVR Butterfly trackers use the nRF52833 MCU
Published on February 12, 2026, the entry describes open-hardware virtual-reality trackers combining IMUs, an nRF52833 wireless MCU, and a custom 2.4 GHz ESB protocol.
Read articleKnowledge you can apply
Radar
Daily bookmarks: relevant news, facts and discoveries.
Three approaches to on-policy self-distillation
Published on February 12, 2026, the article examines OPSD, SDFT, and SDPO, on-policy self-distillation methods using denser feedback, as well as benchmarks and limitations.
Read articlevLLM announces streaming inputs and a WebSocket API
Published on February 11, 2026, the vLLM blog describes streaming inputs and a real-time WebSocket API for applications that process audio, video, and other data incrementally.
Read articleBeelink ME Pro combines SATA, M.2 and 5GbE
Announced on February 10, 2026, the Beelink ME Pro combines a compact NAS and mini PC form factor, two SATA bays, up to three M.2 NVMe sockets, and 5GbE networking.
Read articleROME explores segment-level credit for agent training
A 3-billion-parameter model uses segment-level rewards, rather than assigning credit only by token or trajectory, to train agents that use tools.
Read articleBM25 ranks documents without embeddings
Published on February 9, 2026, the post explains how BM25 scores search results using term rarity, diminishing returns for repeated terms, and document length normalization, without requiring training, embeddings, or fine-tuning.
Read articleLatentMoE distributes heads across GPUs
A February 9, 2026 post describes a LatentMoE design with head parallelism and reports up to 1.61× speedup over standard MoE with expert parallelism.
Read articleLocal Studio PR proposes ROCm, speech, image, and video support
Published on February 9, 2026, a Local Studio pull request describes proposed ROCm support and a speech mode with TTS/STT using ACE-Step and Whisper v3 Large. The proposal also mentions images and video.
Read articleMaxRL proposes likelihood training for binary-reward RL
Published on February 9, 2026, the post presents MaxRL: additional rollouts approximate maximum-likelihood training with non-differentiable sampling. The post says the method reduces underweighting of difficult prompts and achieves up to 20× greater test-time efficiency than GRPO.
Read articleHex-Rays: a presentation on microcode
Published on February 9, 2026, the entry describes a presentation on the internals of the Hex-Rays decompiler in IDA Pro, including microcode. The post points to a video and a PDF.
Read articleREMnux connects AI agents to more than 200 tools
Published on February 9, 2026, the report describes a REMnux MCP server connecting AI agents to more than 200 malware-analysis tools and offering guidance on selecting them and interpreting results.
Read articleGoogle Research presents Sequential Attention
On February 9, 2026, Google Research presented an approach that selects features or layers during training to seek leaner, faster models without sacrificing accuracy.
Read articleVulnLLM-R-7B analyzes code vulnerabilities
Published on February 9, 2026, VulnLLM-R-7B is presented as a reasoning model that searches code for vulnerabilities by examining data and control flows.
Read articleVOLT: an open-source GPU compiler
An article published on February 8, 2026 introduces VOLT, an open-source GPU compiler, and discusses emerging open GPU architectures that define SIMT features.
Read articleResearch explores generalizable activations
A February 7, 2026 publication reports using AlphaEvolve to search for activation functions, as part of broader research into discovering AI architectures.
Read articleOpen-source repository explores voice agents
Published on February 6, 2026, the repository offers engineers a starting point for creating voice agents with open-source models.
Read articleHow GPUs Evolved from SIMD to SIMT
An ACM SIGGRAPH Blog article, published on February 5, 2026, describes how GPUs combined thread abstractions with SIMD hardware, becoming flexible processors for graphics, AI, and scientific computing.
Read articleEight ways to implement defer in C
An article compares eight approaches to implementing defer in C and discusses portability and cleanup patterns.
Read articleGuide covers tool calling with local LLMs
Published on February 5, 2026, the guide presents function-calling examples with open models: stories, Python execution, terminal calls, and mathematics.
Read articleVeritensor 1.4.0 broadens the project's scope
Announced on February 5, 2026, version 1.4.0 is described as a major update that expands a model scanner project into an AI security platform.
Read articleRota Nacional
Bring privacy into your workflow.
30 days, no card, with a starting quota. After that, Pix credit from R$ 10,00.