odyss3y

odyss3y

AI & ML interests

Red-teaming and bias testing LLMs with a focus on refusals, alignment cracks, and narrative integrity (Banes Benchmark). Cybersecurity/DFIR background, SDXL tinkerer, long-term interest in multimodal tech for home and elder care.

Recent Activity

new activity about 1 month ago

QuantFactory/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF:🚩 Report: Spam

reacted to mitkox's post with 🔥 about 2 months ago

XBai o4 claims to beat Claude Opus 4 and o3-mini, and they provide verifiable proof. My skepticism circuits overloaded, but my local AI FOMO module screamed louder. I've thrown this 33B monoblock LLM onto a single GPU and used Roo Code for some… let’s call it “vibe testing”. It’s terrifyingly competent. As an architect, it’s the best open-weight model I’ve touched this side of 2025.

new activity about 2 months ago

DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS:Update README.md

View all activity

Organizations

None yet

odyss3y 's datasets

None public yet