Hacker NewsLLM Architecture Gallery — 45+ Model Diagrams Surges to 443pts, 34cmtsSebastian Raschka·medium signalXBlueskyLinkedInCopy linkSebastian Raschka's LLM Architecture Gallery hit 443 points after posting March 15-16, covering architecture diagrams and fact sheets for 45+ models from 3B to 1T parameters. Covers dense models (Llama 3, Gemma 3, OLMo 3), sparse MoE (DeepSeek V3/V3.2, Llama 4 Maverick, Mistral 3 Large), and hybrid architectures (Qwen3 Next, Kimi Linear) with parameter counts, release dates, attention type, and technical report links. Physical high-resolution poster available.SourceSource pageSebastian Raschka↳ Follow the threadPolicy dependency / Stack layerCROSS-CATEGORY: Three Independent Agent-Action Gates Shipped in 48 Hours, All Judging the Command Against Stated IntentProduct Hunt, github.com/AGGIB/Stroq and rewarelabs.com (three independent sources; the 72% figure is Reware's own)Policy dependency / Stack layerA Fine-Tuned 4B Qwen in 2.6 GB Beats GPT-5.6 on a Transit-Kiosk Agent Benchmark, and PEFT Gains Vanish by 27BarXiv 2609.10016Stack layer / Threat pattern16% of 3,171 public agent-harness setups carry a confirmed security defect, and 3.8% ship a skill that pre-approves your shellarXivPolicy dependency / Stack layerAgents hit 80% F1 deciding whether a dependency CVE is exploitable, but fall below 70% explaining whyarXiv 2609.08040Policy dependency / Stack layerAnthropic Gave EU Cybersecurity Agency ENISA Access to Mythos 5, Three Months After Release, and Still Withholds 5.1BloombergPolicy dependency / Stack layerPaul Christiano Joins the OpenAI Foundation Board and Its Safety and Security CommitteeOpenAI BlogPolicy dependency / Stack layerHawley Opens a Senate Investigation Into OpenAI's Handling of the Hugging Face Breach, 16 Questions Due October 1AxiosStack layer / Threat patternblock/goose 1.50.0 deletes fast model routing and the managed model registry for local inferenceGitHub