Fine-Tuning Qwen2-VL for Blockchain Graph Classification on AMD MI300X: What the Docs Don’t Tell You

Blockchain Graph Classification with Vision-Language Models

The Problem: Blockchain Forensics Needs Vision, Not Just Text Graph renderings of blockchain transactions carry topology signals that serialize badly into token sequences. A hub node surrounded by 47 short-lived leaf wallets looks like a table of addresses and amounts in text form — recognizable only if you already know the pattern. Rendered as an … Read more

Fine-Tuning Qwen2-VL on AMD MI300X for Blockchain Graph Classification: What the Docs Don’t Tell You

Blockchain Graph Classification with Qwen2-VL on AMD MI300X

The Problem: Blockchain Security Needs Visual Reasoning, Not Just Embeddings Graph visualizations of blockchain transactions contain structural signals that are essentially invisible to embedding-based classifiers. A peel-chain mixer produces a distinctive fan-out pattern — one input, many outputs at near-identical amounts — that shows up immediately as a visual motif but gets washed out when … Read more

Speakr v0.8.19: What Actually Changed and Whether It’s Worth Upgrading Your Self-Hosted Transcription Stack

Speakr v0.8.19 upgrade, self-hosted transcription stack

The Problem Speakr Is Solving (And Who It’s Actually For) Cloud transcription pricing has a nasty compounding effect: you don’t notice it until you’re processing a backlog of three-hour interview recordings and the monthly invoice arrives. AssemblyAI and Deepgram both bill per audio-minute, which sounds reasonable until your podcast archive hits four figures in hours, … Read more

Code Mode + MCP: Wiring Your Local LLM Into a Real Development Workflow

Integrating Local LLM into Development Workflow

The Problem: Your AI Coding Assistant Lives in a Walled Garden The hallucination that wastes the most time isn’t a wrong algorithm — it’s a wrong tool call. Your LLM confidently writes prisma db pull –schema=./prisma/schema.prisma against a database that’s actually on a non-standard port behind a tunnel, or generates a Docker Compose service block … Read more

fedit: A Deterministic CLI + MCP File Editor for LLMs That Can’t Stop Mangling Your Configs

LLM file editing issues

The Problem: LLMs Are Terrible at Surgical File Edits The first time an LLM helpfully rewrote my entire nginx.conf because I asked it to add a single proxy_pass directive, I didn’t notice until the site started returning 502s. The model had quietly dropped two map blocks, reordered the server contexts, and normalized all my tab … Read more

AI Coding Tools Are Now a CVSS 10.0 CI/CD Supply Chain Vector — What to Patch and What to Audit

AI Coding Tools Security

The Attack Surface Nobody Audited Until Now Most people treating their AI coding assistant as a smarter autocomplete have not thought carefully about what it can actually do on their machine. Cursor, Gemini CLI, and similar agentic tools operate with filesystem read access, shell execution, and in many configurations the ability to stage and push … Read more

Vibe Coding Day-to-Day: A Week in My Git Log, the 10% I Never Delegate, and Which Tool Actually Does What

The Feature Ticket I Opened Monday Morning (And Exactly What Happened Next) ## The Feature Ticket I Opened Monday Morning (And Exactly What Happened Next) Here’s the prompt I dropped into Cursor at 9:04 AM: Add a WishlistButton.tsx component that calls useCartUpdate.ts on toggle. Button should be optimistic — update UI immediately, roll back on … Read more