#agentswarm — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #agentswarm, aggregated by home.social.
-
New piece: Moonshot AI just open-sourced a model running 300 autonomous agents for 12 hours at ~$50 total. Your paralegal costs more per hour than the entire attack. Your firewall sees nothing. Your IPS has no signature. This is Cognitive DDoS -- Distributed Denial of Staff. The Botnet Grew a Brain:
#CyberSecurity #AI #AgentSwarm #SocialEngineering #InfoSec #ProfessionalServices #Governance #ThreatIntelligence #OpenSource -
أطلقت شركة Moonshot AI نموذجها الرائد Kimi K2.6، الذي يقدم ميزات ترميز متقدمة ونظام وكلاء تعاوني متطور. يتميز بقدرات ترميز قوية بلغات مثل Rust و Go و Python، ويحول النصوص لواجهات أمامية تفاعلية، ويدعم تطويرًا كاملاً بسيطًا. كما يتيح نظام "Agent Swarm" تنسيق وكلاء متخصصين للبحث وتحليل المستندات وتوليد محتوى متعدد التنسيقات. النموذج متاح الآن عبر Kimi.com وتطبيق Kimi وواجهة برمجة التطبيقات و Kimi Code.
-
#Kimi K2.6, the latest #opensource model, showcases advancements in #coding, #longhorizon execution, and #agentswarm capabilities. It excels in complex #engineering tasks, demonstrating significant improvements in #codegeneration accuracy, #longcontext stability, and #toolinvocation success rate compared to its predecessor. https://www.kimi.com/blog/kimi-k2-6?eicker.news #tech #media #news
-
#Kimi K2.6, the latest #opensource model, showcases advancements in #coding, #longhorizon execution, and #agentswarm capabilities. It excels in complex #engineering tasks, demonstrating significant improvements in #codegeneration accuracy, #longcontext stability, and #toolinvocation success rate compared to its predecessor. https://www.kimi.com/blog/kimi-k2-6?eicker.news #tech #media #news
-
#Kimi K2.6, the latest #opensource model, showcases advancements in #coding, #longhorizon execution, and #agentswarm capabilities. It excels in complex #engineering tasks, demonstrating significant improvements in #codegeneration accuracy, #longcontext stability, and #toolinvocation success rate compared to its predecessor. https://www.kimi.com/blog/kimi-k2-6?eicker.news #tech #media #news
-
🚀 #MoonshotAI releases #KimiK26 — #opensource 1T-param MoE model, 32B active params, 262K context & native multimodal (image + video) input
🧠 +15% over K2.5 on benchmarks: better long-horizon coding stability, deeper reasoning & stronger instruction following #AI #LLM
🤖 #AgentSwarm now scales to 300 parallel sub-agents coordinating 4,000 steps simultaneously — up from 100 agents in K2.5
🧵 👇
-
🚀 #MoonshotAI releases #KimiK26 — #opensource 1T-param MoE model, 32B active params, 262K context & native multimodal (image + video) input
🧠 +15% over K2.5 on benchmarks: better long-horizon coding stability, deeper reasoning & stronger instruction following #AI #LLM
🤖 #AgentSwarm now scales to 300 parallel sub-agents coordinating 4,000 steps simultaneously — up from 100 agents in K2.5
🧵 👇
-
🚀 #MoonshotAI releases #KimiK26 — #opensource 1T-param MoE model, 32B active params, 262K context & native multimodal (image + video) input
🧠 +15% over K2.5 on benchmarks: better long-horizon coding stability, deeper reasoning & stronger instruction following #AI #LLM
🤖 #AgentSwarm now scales to 300 parallel sub-agents coordinating 4,000 steps simultaneously — up from 100 agents in K2.5
🧵 👇
-
🚀 #MoonshotAI releases #KimiK26 — #opensource 1T-param MoE model, 32B active params, 262K context & native multimodal (image + video) input
🧠 +15% over K2.5 on benchmarks: better long-horizon coding stability, deeper reasoning & stronger instruction following #AI #LLM
🤖 #AgentSwarm now scales to 300 parallel sub-agents coordinating 4,000 steps simultaneously — up from 100 agents in K2.5
🧵 👇
-
🚀 #MoonshotAI releases #KimiK26 — #opensource 1T-param MoE model, 32B active params, 262K context & native multimodal (image + video) input
🧠 +15% over K2.5 on benchmarks: better long-horizon coding stability, deeper reasoning & stronger instruction following #AI #LLM
🤖 #AgentSwarm now scales to 300 parallel sub-agents coordinating 4,000 steps simultaneously — up from 100 agents in K2.5
🧵 👇
-
🚀🤖 Behold the rise of Agent Swarm, the latest buzzword salad tossed with AI dressing! Now you, too, can automate every developer's existential crisis as they watch code write itself into oblivion. 🌪️🖥️ Because who needs creativity when you've got a swarm of self-learning drones to handle your "innovations"? 🙄
https://github.com/desplega-ai/agent-swarm #AgentSwarm #AIautomation #DeveloperDilemma #SelfLearningTech #InnovationDisruption #HackerNews #ngated -
#Kimi K2.5, the most powerful #opensource model to date, excels in #coding and #vision capabilities. It can self-direct an #agentswarm for complex tasks, reducing execution time by up to 4.5x. Kimi K2.5 is available via Kimi.com, the Kimi App, the API, and Kimi Code, with Agent Swarm currently in beta on Kimi.com. https://www.kimi.com/blog/kimi-k2-5.html?eicker.news #tech #media #news