TGINSIGHT SIMILAR POSTS
Source channel @githubtrending · Post #15314 · Dec 6
#python#brain_inspired_ai#deep_learning#large_language_models#reasoning The Hierarchical Reasoning Model (HRM) is a new type of AI that reasons more like a human brain, using a fast part for quick details and a slow part for big-picture planning. It solves hard logic tasks like Sudoku, mazes, and IQ-style puzzles very well, even though it is tiny (only 27 million parameters) and learns from very little data (just 1,000 examples). Unlike most large language models, it does not need long chains of written reasoning steps or huge amounts of training, which makes it much faster, cheaper, and more efficient. For the user, this means powerful reasoning in a small, fast system that can run on ordinary hardware and still beat much larger models on tough problems. https://github.com/sapientinc/HRM
Search: #kfunc
@aigcrubbish · Post #158 · 01/27/2026, 05:06 PM
[$] Implicit arguments for BPF kfuncs Linux 内核的 kfunc 机制允许 BPF 程序直接调用内核函数。目前内核中有超过 300 个 kfunc，功能涵盖字符串处理（如 `bpf_strnlen()`）到自定义调度器（如 `scx_bpf_kick_cpu()`）等。 有时，这些 kfunc 需要访问 BPF 程序无法直接获取的上下文信息，因此无法通过参数传递。Ihor Solodrai 提交的“隐式参数”补丁集旨在解决这个问题，它允许 kfunc 隐式地接收额外的上下文参数。 原文链接：https://lwn.net/Articles/1055559/ #Linux#内核#BPF#kfunc #AIGC Read more