Tech

Z-Image-Distilled - a Z-Image derivative that keeps diversity while speeding up inference

An overview of Z-Image-Distilled, the distilled fast-inference variant of Z-Image, including how it compares with FLUX.1 Schnell, how it runs on an M1 Max 64GB machine, and LoRA compatibility.

Running FLUX.2 Klein 9B on Apple Silicon Macs

Overview of Black Forest Labs' FLUX.2 Klein 9B model and how it performs on M1/M2/M3/M4 Macs. Covers the key factors behind the CUDA vs MPS performance gap, including memory bandwidth and FP8 quantization.

Agent Lightning: Microsoft's reinforcement learning framework for AI agents

Microsoft released an open-source framework that can optimize almost any AI agent with reinforcement learning, with little to no code changes. It supports arbitrary frameworks such as LangChain, AutoGen, and Claude Agent SDK.

MarkItDown - Microsoft's Python tool for turning documents into Markdown

A Microsoft tool that converts PDFs, Word, Excel, PowerPoint, and more into Markdown. It also fits into LLM pipelines and supports an MCP server.

KugelAudio — Open‑Source 7B‑Parameter TTS (ComfyUI‑Compatible)

Text‑to‑Speech covering 24 European languages with voice cloning. An open‑source model that outperformed ElevenLabs in the authors’ A/B tests.

I looked into OpenRouter's free models and Free Router

A summary of how OpenRouter's free models work, the rate limits involved, and the caveats you should know before using them in agents.

Notepad++'s official updater was hijacked

A breakdown of how Notepad++'s WinGUp updater was hijacked through a hosting provider compromise and used to serve malicious binaries to selected users.

Power Sampling: unlocking LLM reasoning without reinforcement learning

A look at how changing the inference-time sampling strategy can improve LLM reasoning performance without retraining on RL.

PageIndex - tree RAG with LLM reasoning only, no vector search

I looked into PageIndex, a RAG system that builds hierarchical document trees using only LLM reasoning, without chunking or vector databases. I also consider how it fits with layout detection and OCR pipelines.

Video Generation AI: January 2026 Update Roundup and Where i2v Stands

This article organizes the major video-generation AI updates announced in January 2026 and examines whether i2v (image→video) is practically usable, including models that run locally.

Gemini starts generating images even when you did not ask it to

A report on the issue where Gemini starts generating images even when you are only asking about images, along with current workarounds.

Gradience: a tool that audits whether your LoRA rank is actually necessary

An introduction to Gradience, a tool that quantifies whether a LoRA rank setting is excessive using singular value decomposition. In experiments on Mistral-7B, halving the rank improved accuracy.