Could it have been built solely with llm+tools/mcp as the product? Everything I build with vibes gets overbuilt by default and finding myself thinking of how much to strip back to just llm plus tools. It’s worked perfectly for a couple of things I tried but ofc depends on if
CODE
-
Linear MCP Server Enables Agentic Task Automation
By
–
The linear remote MCP server is great. It connected to @Lutra_AI seamlessly and we are now able to do agentic tasks like "Get me all tickets closed in the last week, summarize and put in a google doc, slack to # marketing every friday" Super cool.
-
Lutra AI MCP Client for Work Automation Integration
By
–
Would love for you to add @Lutra_AI to the map! We have an MCP client focused on work automation that fully supports the latest MCP remote server protocols – super smooth!
-
Lutra_AI Now Supports MCP Server Integration
By
–
@Lutra_AI supports this today as well! Just put in a MCP server URL and it works, come try it!
-
Free Course: Pretraining LLMs with Upstage and DeepLearning.AI
By
–
Explore "Pretraining LLMs," a short course developed with @upstageai. DeepLearning.AI (@DeepLearningAI) Explore "Pretraining LLMs," a short course developed with @upstageai. While prompting or fine-tuning existing models is effective for many general language tasks, pretraining becomes essential for specialized domains or underrepresented languages in current models. This course guides you through the LLM pretraining pipeline—from data preparation to model evaluation—and introduces depth up-scaling, an innovative technique used by Upstage to train their Solar model family, cutting pretraining compute costs by up to 70%. Take the course for free: hubs.la/Q03kT_FP0 — https://nitter.net/DeepLearningAI/status/1918365268293607723#m
-
CodeLLM Generates Code from Mockups and Screenshots
By
–
With CodeLLM, you can upload mock-ups and screenshots and generate code.
-
Building apps using AI vision and vibes in 2025
By
–
No frontend, no backend, just vision + vibes = app. This is how builders win in 2025.
-
Extreme PyTorch: ML Workloads and AI Agents Challenges
By
–
writing out my Keynote at @MLSysConf this year and I'm pretty excited!
"Extreme PyTorch: Inside the Most Demanding ML Workloads—and the Open Challenges in Building AI Agents to Democratize Them" -
PDF RAG Agent with Agno and Milvus Vector Database
By
–
PDF RAG Agent using Agno and Milvus!
— Sumanth (@Sumanth_077) 2 mai 2025
I’ve built a PDF RAG agent that pulls context from indexed PDF files stored in a local vector database.
If needed, it can fall back to web search to provide more relevant answers.
100% open source. Here's a step-by-step guide: https://t.co/IjNO8yT8oq pic.twitter.com/pJCy2vFyCPPDF RAG Agent using Agno and Milvus! I’ve built a PDF RAG agent that pulls context from indexed PDF files stored in a local vector database. If needed, it can fall back to web search to provide more relevant answers. 100% open source. Here's a step-by-step guide:
-
Malicious PyPI Packages Exploit Gmail and Websockets for System Hijacking
By
–
Malicious #PyPI packages abuse #Gmail, websockets to hijack systems! https://
search.app/V4mPv #vulnerability #2fa #RCE #ZeroTrust #ZeroDay #cybercrime #hacker #privacy #APT #bot #CISO #DDoS #hacking #phishing #CyberAttack #cybersecurity #Security #infosec #AppSec #CyberSec