Skip to content

/

ZeroHour

ZeroHour aggregates public sources — security and AI press, vendor advisories, NVD, CISA KEV, FIRST EPSS, leak-site trackers and Have I Been Pwned — and classifies them with AI. Summaries can be wrong: read the original. All times are UTC.

News CVEs Incidents Tags Daily brief Traffic Sources RSS & API Kiosk Health Sitemap

Home
News feed
Exploited now

Security

CVEs
Ransomware & breaches
Threat actors & entities
IOCs

AI

AI & models

Explore

Tags
Daily brief
Analytics
Traffic & readers
Ask the feed
Sources

You

Watchlist
Saved
RSS, API & alerts

07:57 UTC· 12m ago

#moe — news, CVEs and analysis · ZeroHour

today 47 visits · 60 views · 7 reads·all time 17K views

Tag

#moe

1 stories this week · 15 this month · 16 in 6 months · mostly AI

stories per day · 30 days

Related#open-weights 6 #long-context 4 #llm 3 #multimodal 3 #deepseek 2 #inference 2 #kv-cache 2 #quantization 2 #qwen3.5 2 #256k-context 1 #agentic-ai 1 #agentic-coding 1 #agentic-models 1 #aliceai 1 #alignment 1 #amap 1 #architecture 1 #atria-dawn 1

16 stories, newest first · one card per story

Hacker News · security·3d ago

Tokens Too Cheap to Meter

#llm #inference #cost-trends

AI industry

14 min

Hugging Face daily papers·9d ago

IntBMoE: Integrating Block-Level Conditioning into Expert Composition for Full-Participation Mixture-of-Experts

#amap #architecture #deep-learning

Hugging Face daily papers·10d ago

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

#deepseek #inference-efficiency #kv-cache

1

Hugging Face trending models·10d ago

AlexWortega/openjev — new model trending #30 on Hugging Face

#cross-encoder #hugging-face #moe

Model release

2 min

Hugging Face daily papers·11d ago

The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction

#consumer-hardware #edge-inference #inference

arXiv cs.AI / cs.LG / cs.CL·11d ago

What Breaks Under Pruning in Smart Homes, and When? Evaluating LLM Degradation Across Architectures and Task Complexity

#llm-compression #model-degradation #moe

AI research

Hugging Face daily papers·14d ago

Flattening Every Memory Peak in Long-Context Mixture-of-Experts Training

#distributed-training #long-context #memory-optimization

1

Hugging Face trending models·14d ago

yandex/AliceAI-Foundation-80B-A3B-Base — new model trending #30 on Hugging Face

#aliceai #base-model #llm

Model release

15 min

Hugging Face trending models·15d ago

internlm/Atria-Dawn-Preview — new model trending #30 on Hugging Face

#256k-context #agentic-ai #atria-dawn

Model release

15 min

Hacker News · AI·16d ago

Cognition's SWE-2 achieves 92.8 on Terminal-Bench 2.1

#agentic-coding #benchmarks #cognition

2 min

MarkTechPost·17d ago

DeepSeek AI Released DeepSeek-V4.1-Flash with 1M Context, FP4 KV Cache, and Cross-Layer Attention Reuse

#deepseek #deepseek-v4.1-flash #kv-cache

4 min2

arXiv cs.CR·18d ago

How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoE

#alignment #directional-ablation #glm

AI safety & security

Hugging Face daily papers·18d ago

LLaDA-UI: Bringing Block-wise Diffusion to Vision-Language GUI Agents

#diffusion-lm #grounding #gui-agent

Hugging Face trending models·18d ago

Edge0/Edge0-35B-A3B-preview — new model trending #30 on Hugging Face

#edge0 #lora #mlx

Model release

4 min

Hugging Face trending models·18d ago

nex-agi/Nex-N2.5-Pro — new model trending #30 on Hugging Face

#agentic-models #computer-use #moe

Model release

13 min1

Hugging Face trending models·Aug 26, 2026

unsloth/Qwen3.8-Flash-Next-GGUF — new model trending #21 on Hugging Face

#gguf #long-context #moe

Model release

15 min1