Tech

Can FLUX.2 Klein NSFW LoRAs actually run on an M1 Max?

Investigated whether NSFW LoRAs for FLUX.2 Klein 9B can run on M1 Max 64GB. Covers model compatibility, LoRA application paths, RunPod verification strategy, and VRAM requirements for training your own LoRA with ai-toolkit.

De-distilling Z-Image-Turbo for LoRA Training

How the de-distill training adapter works for Z-Image-Turbo LoRA learning, SDXL LoRA incompatibility with Z-Image, and caption considerations specific to the Z-Image ecosystem.

Barman Was Not a Drop-in Replacement for pgBackRest

A real-world migration from pgBackRest to Barman on Railway reveals the operational cost increase in container environments and the importance of WAL slot monitoring.

Fine-Tuning Reignites Verbatim Memorization of Copyrighted Books in LLMs

An arXiv paper reports that fine-tuning GPT-4o, Gemini 2.5 Pro, and DeepSeek-V3.1 on summary-to-text expansion tasks increases verbatim reproduction of copyrighted books.

Adding Working Memory to Claude Code with CTX

A read of CTX, which auto-injects context into Claude Code via the UserPromptSubmit hook. Compared with auto-memory, YourMemory, WUPHF, and Cloudflare Agent Memory on persistence and storage. Also looked at why 1M context still isn't enough and how each agent architecture uses its window differently.

What Actually Worked for Chrome Web Store SEO After Publishing 18 Extensions

Practical findings from someone who published 18 Chrome extensions over 6 months: what moved installs (titles, short descriptions, screenshots, review prompts) and how the Manifest V2 to V3 migration affects install rates.

Running Apache Airflow 3.2.0 with PostgreSQL and Executing Your First DAG

Steps to set up Apache Airflow 3.2.0 with a PostgreSQL metadata database, run your first DAG, and configuration notes for moving beyond standalone mode.

Stripe Checkout Price Tampering Vulnerability

If your Stripe Checkout endpoint takes amount or priceId from the request body, users can swap prices and plans. Pin pricing decisions to the server.

A FastAPI wrapper that takes Japanese, runs it through Ollama, and routes to ComfyUI or mflux to drive Anima, WAI-IL, and FLUX.2 Klein from one WebUI

Three local image generation engines (WAI-Anima, WAI-IL/SDXL, FLUX.2 Klein 4B) tied together by a thin FastAPI wrapper that takes Japanese prompts. Ollama (gemma3:12b) handles JP→EN, ComfyUI workflows are built on the fly in Python, FLUX.2 runs as an mflux subprocess, and the whole thing is reachable from an iPhone over Tailscale.

Lessons from VoteWise AI on Building Election Guides with Next.js and Gemini 2.5 Flash

VoteWise AI turns election education into a multilingual chat, voice, and story-mode experience built on Next.js. Notes on designing around Gemini 2.5 Flash's safety filters in a political context.

Wiring Up a Multimodal Japanese Local RAG with FastAPI, Chroma, Open WebUI, and Ollama on M1 Max

Hands-on log of building the DEV article's PDF RAG on M1 Max 64GB, extending it with images via CLIP, and pushing through Japanese with bge-m3 + Qwen3.6 35B. Documents the modality gap, the dual inference server crash, and LLM-jp 4-8B's empty chat template silently dropping the system role.

Reading an Article on Building a Local PDF RAG with FastAPI, llama.cpp, Chroma, and Open WebUI

Notes on a DEV Community article that wires up FastAPI as an OpenAI-compatible RAG API layer with llama.cpp, Chroma, and Open WebUI, plus where the architecture fits and what to watch for.