GENERATIVE AI

→ View original post on X — @plinz

LLMs as Savants: Memorization Versus Derivation Pain

By

@plinz

–

15 June 2025 14h43

Memorization is easier but less useful than thought, which is why memorization needs to be a more painful activity than derivation. Savants can be immune against this pain, and LLMs are savant AI.

→ View original post on X — @akshay_pachaar

Training an LLM Using Another LLM: Advanced AI Approach

By

@akshay_pachaar

–

15 June 2025 12h44

Train an LLM using another LLM!!

→ View original post on X — @jeremyphoward

LLMs Performance Degradation at Critical Thresholds

By

@jeremyphoward

–

15 June 2025 9h40

Yeah all LLMs suddenly become *extremely* dumb when you hit that point.

→ View original post on X — @elliotchen100

Full-stack Chat AI library with React LangGraph Gemini

By

@elliotchen100

–

15 June 2025 8h15

发现一个有趣的库，一键搭一个全栈 Chat，
前端 @reactjs 后端 @langchain LangGraph gemini-fullstack-langgraph-quickstart – 开源
直接构建 research-augmented conversational AI 亮点 • 前端基于 React，后端基于 LangGraph 和 FastAPI • 利用 Gemini 大模型自动生成搜索词，动态调用

→ View original post on X — @elliotchen100

Bilive: Automated Live Stream Recording and AI-Powered Video Processing

By

@elliotchen100

–

15 June 2025 7h50

发现一个 B 站专属全自动，识别，切片，上传的工具 bilive – 自动化程度高，兼容强 – 人人都是录播员亮点
• 支持 7 x 24 小时无人值守录制 B 站直播
• 自动渲染弹幕、识别字幕并合成到视频
• 根据弹幕密度自动切片，生成精彩片段并自动上传
• 集成多模态大模型，自动生成切片标题和视频封面

Understanding Prompt Injection Attacks in LLMs

By

–

15 June 2025 7h22

What is a Prompt Injection Attack? https://
wiz.io/academy/prompt
-injection-attack
… #zeroclick #ArtificialIntelligence #AI #security #vulnerability #CyberSec #M365 #Copilot #LLMs #LLM #GenAI #promptinjection #promptengineering #prompt

Zero-Click AI Vulnerability Exposes Microsoft 365 Copilot Data

By

–

15 June 2025 7h20

Zero-Click AI Vulnerability Exposes Microsoft 365 Copilot Data Without User Interaction! https://
thehackernews.com/2025/06/zero-c
lick-ai-vulnerability-exposes.html?m=1
… #zeroclick #ArtificialIntelligence #AI #security #vulnerability #CyberSec #M365 #Copilot #LLMs #LLM #GenAI #promptinjection #promptengineering #prompt @fogle_shane

Google’s Defense Against Indirect Prompt Injection Attacks Gemini

By

–

15 June 2025 7h15

Google's Multi-Layer Defense Against Indirect Prompt Injection Attacks on Gemini AI https://
search.app/RWTQh #GoogleGemini #Geminiai #LLMs #LLM #AI #ArtificialIntelligence #GenAI #prompt #Injection #Security #Tech #technology @SpirosMargaris @PawlowskiMario @mvollmer1 @gvalan

Organizations Unprepared for Agentic AI Risks and Challenges

By

–

15 June 2025 4h59

Organizations Aren’t Ready for the Risks of Agentic AI https://
search.app/SmE1o #RAG #AgenticAI #AIagentInnovation #AIAgents #LLMs #LLM #GenerativeAI #GenAI #technology #TechRevolution #tech #Engineering #ArtificialIntelligence #AutonomousIntelligence #AI @sonu_monika @enilev