AI, automation & information security
Patrick Gawron
Agentic workflows, local-first AI, secure business logic. Daily AI experiments, consulting projects - and a build log of coding sidequests.
Tools
Notes
Quick posts for everything that doesn't need a full article - local LLMs, CSS, keto. One page each.
Browse all notes >Tech news
Qwen releases Qwen4-Max, with 419 points on Hacker News
Qwen4-Max is announced on the Qwen blog. The source text gives no weights, parameter count or licence, and Max models are usually API-only. Check the blog for open-weight siblings before expecting anything on a 16 to 32 GB card.
VillanovaAI releases Villanova2, a 15B-A3B MoE family with GGUFs
Villanova2 includes a 15.5B total, 3.9B active MoE and a 2.4B dense model, each with base, instruct and VL variants. It covers English, Italian, German, Spanish and French, and GGUFs are in the same collection. Licence is not stated.
Anthropic releases Claude Fable 5.2 and Mythos 5.2, Fable tops Artificial Analysis at 65
API-only, no local weights. Artificial Analysis scores Fable 5.2 at 65, the highest index so far, which resets the bar that open-weight models are measured against. Worth tracking as the frontier reference for local releases.
MiniMax releases H3-Image, an open-weight image model built on H3
Open weights for an image model built on the H3 stack, on Hugging Face. Parameter count, licence and VRAM needs are not in the source text, so check the model card before trying it in ComfyUI on a 16 to 32 GB card.