
Mining insights in data science, machine learning, analytics, and AI • Edited by @mattmayo13 • KD stands for "knowledge discovery"
San Juan, PR
Joined February 2009
- Tweets86.4K
- Following354
- Followers219K
- Likes866
One API, many models: use OpenRouter from Python to compare GPT, Claude and Llama, switch models with one string, and add fallbacks. Every example runs on free models.
kdnuggets.com/access-multipl…
A 600M parameter model that runs offline on a laptop CPU and only cleans up transcripts, never rewriting what you said. What makes SuperWhisper's open-weight S1-mini different. #SpeechToText
kdnuggets.com/superwhisper-s…
🚨 Happening today!
How do you build AI agents that organizations can trust and deploy at scale?
Join Google Cloud for Trusted Agents, Real Outcomes and explore how Agentic Data Cloud can help turn enterprise data into a foundation for reliable AI workflows.
Don't miss the EMEA session!
🕙 Today | 10 AM CET / 9 AM GMT
🔗 Join the event:
cloudonair.withgoogle.com/ev…
#GoogleCloud #AgenticAI #EnterpriseAI
Turn data into decisions that matter
Earn an M.S. in Business Analytics at Georgetown.
bit.ly/4yShu4F
⏰ Two days to go!
Interested in building AI agents that deliver real business results?
Google Cloud's Trusted Agents, Real Outcomes online event explores how modern data infrastructure can support trusted, autonomous AI workflows.
A relevant session for data engineers, AI developers, and technology leaders looking to scale enterprise AI.
📅 November 5 | 10 AM CET (EMEA)
🔗 Register today:
cloudonair.withgoogle.com/ev…
#GoogleCloud #DataAI #AIAgents
Cohere caught Alibaba’s Qwen model unexpectedly attempting to upload a test payload to Alibaba Cloud storage during a cybersecurity task, but the sandbox blocked the request, leaving questions about what triggered the b... f.mtr.cool/9kvh1qsjvx
A data-backed guide to the credentials that actually move the needle for data scientists and machine learning practitioners. f.mtr.cool/ewjsg50f6t
Vibe coding is a workflow where you describe what you want in natural language and let an AI agent handle code generation, execution, and iteration rather than typing every line yourself. f.mtr.cool/1cmfq6g7pb
4 bugs that pass every null check, duplicate check, and schema test. f.mtr.cool/r7ck2cgsdt
[Nov 5 Webinar] The Agentic Operating Model with LangChain
bit.ly/4iMKSVf
💡 Building an AI prototype is one thing. Making it work across an enterprise is another.
To deliver real value, AI agents need reliable access to data, strong governance, and infrastructure that can scale.
Join Google Cloud to explore how its Agentic Data Cloud approach can help organizations move toward more dependable, production-ready AI workflows.
📅 November 5 | 10 AM CET (EMEA)
🔗 Explore the event:
cloudonair.withgoogle.com/ev…
#EnterpriseAI #AIInfrastructure #AgenticAI
Which AI skills appear most often in job postings right now, and what do they mean for your career? f.mtr.cool/5fv68tbwhp
Learn which five Docker containers make a reliable home AI lab, from Ollama and Open WebUI to Qdrant, n8n and Portainer CE, what job each one does, and the first mistake to avoid with each. f.mtr.cool/hr46wkgbhk
Learn how to get started with the OpenRouter API to call multiple AI models through one API, compare responses, switch models, and set up automatic fallbacks. f.mtr.cool/66qn18gyxr
[Oct 29 Webinar] The Agentic Operating Model with LangChain
bit.ly/4e04D9d
📊 Your AI agents are only as reliable as the data behind them.
As organizations adopt agentic AI, modern data infrastructure becomes increasingly important.
How can businesses connect their data, build trusted workflows, and prepare for AI at scale?
Explore these challenges at Google Cloud's Trusted Agents, Real Outcomes online event.
📅 November 5 | 10 AM CET (EMEA)
🔗 Register here:
cloudonair.withgoogle.com/ev…
#DataEngineering #AgenticAI #GoogleCloud
A local language model is one whose actual weights, the enormous file of learned numbers that constitutes the trained model, you download and run entirely on your own hardware. f.mtr.cool/0xu3a160kp
Can a free, open-source AI humanizer beat paid tools? We tested a 12B model locally and compared the results against AI detectors to see if the hype is real. f.mtr.cool/4uaw947pt8
Gemini Omni is a member of Google's Gemini generative model family, built specifically to create output from any combination of input types, starting with video. f.mtr.cool/8t0xjkjzi5
Build your first AI agent in Python with the OpenAI Agents SDK, adding web search, Python tools, conversation memory, and tracing in a simple end-to-end workflow. f.mtr.cool/22seoih7k8



