An overview of Kimi K2.5’s technical highlights from Moonshot AI: a 1T-parameter MoE architecture, the MoonViT vision encoder, Agent Swarm (PARL), benchmark results, and more.
A comparison of the hook features offered by Gemini CLI, Claude Code, and Codex CLI. The differences in design philosophy are more interesting than I expected.
Overview of Alibaba’s Z-Image and how it compares to FLUX and Stable Diffusion. A 6B-parameter model that runs on low VRAM and ranks first among open-source models.
Baidu's PaddleOCR-VL-1.5 reaches 94.5% accuracy on OmniDocBench v1.5 with just 0.9B parameters, surpassing large models such as GPT-4o and Qwen2.5-VL-72B.
How should memory be allocated in reasoning models? This paper explains the trade-offs among quantization, KV cache, and test-time compute, based on 1,700 experiments.
An unsafe deserialization vulnerability was found in PHPUnit's PHPT test runner. This article summarizes the risk to CI/CD pipelines and how to mitigate it.
I investigated VNCCS, a character-sprite generation suite for visual novels, and its QWEN Detailer utility. Can it help generate side twin-tails more reliably?
A high-severity stack buffer overflow was found in OpenSSL 3.0 through 3.6. The CMS AuthEnvelopedData path can be attacked without authentication. Update now.
A thinking block corruption error crashed my Claude Code Web session and wiped uncommitted files. An investigation into the cause, workarounds, and whether the files can be recovered.
An explanation of a new attack technique that abuses GitHub’s fork feature and commit display behavior to distribute malware via links that look like official repository URLs.
