My timeline is now full of second brain posts and honestly, the algorithm is doing a great job.
Dr. Vivian Balakrishnan’s post about building his own AI agent system went viral for good reason. It sparked a lot of discussion. And a few of those threads converged for me personally
There are now over 2 million AI models on Hugging Face, and that number passed 700,000 as far back as mid-2024, growing exponentially since.
Yet most people are still arguing about four of them.
Grok. ChatGPT. Claude. Gemini.
#genai#chatgpt#llm#claude#grok
When people compare Claude to Gemini in their coding skills, they are comparing apples and oranges.
Claude isn't an LLM. It's a coding application: it has multiple "agents" responsible for calling various tools, such as searching files containing specific keywords and extracting snippets around the matches, or creating a test script and running it.
Gemini is a pure LLM with reasoning steps. Pure reasoning, while it significantly improves an LLM's skill compared to an LLM answering right away, is not as effective for solving complex coding problems because complex coding requires not just thinking step by step, but also obtaining the actual step outcome when the step involves applying a function to some input and observing the output.
The thinking in LLMs tries to simulate the execution of the code, but a simulation is never perfect. It’s like an LLM can pretend to be a Linux terminal, but it cannot *be* a Linux terminal.
I hope Google is working on an agentic system for coding, and hopefully, it will be part of the Gemini UI. But right now, if you use Gemini, you use one LLM in a vanilla way, while when you use Claude, you use a multi-agent system capable of using coding-specific tools.
AI consulting isn’t about picking the “best” tool. It’s about how different tools fit together.
Like combining LEGO sets, the real creativity comes from how you connect, adapt, and recombine parts into something new.
#ai#ollama#lego
Large language models absorb these patterns from billions of texts, then generate writing that passes the “sounds right” test every single time.
But here’s the problem: fluency isn’t truth.
https://t.co/TUHNnY8cYi
It’s good practice to cheer on the people who are trying to make a difference / self improve / or just being entrepreneurial. I look up to a lot of people for the talents they have and for the amount of work they put into their craft or expertise.
Do we still need schools?
Yes! For socialization, play, and growing up together. But when it comes to personalized, 1-to-1 learning, AI might just be the best tutor we’ve ever had."
https://t.co/xvEPEPIbvh
#DoWeNeedSchool#AIinEducation#SocialLearning#FutureOfSchool#EdTech
"Where does human instinct fit in with AI? AI runs on data and logic—but we make decisions with gut, emotion, and experience. In a world of algorithms, instinct might be our last true edge.”
Hashtags:
#AIvsInstinct#HumanIntuition#AIEthics#DecisionMaking#HumanEdge
Can a bot really handle customer service and should it?
In this episode of Pause & Play AI, Elliott Danker and I dive into how custom GPTs and no-code tools like Flowise are changing the game for customer support.
ICheck it out: https://t.co/RyGfIlpZHA
OpenAI quietly dropped a 34-page technical manual on building AI agents that 99% of people will never read.
I spent 3 days coding every single pattern they revealed.
Here's the practical guide to autonomous AI agents:🧵
Turns out, my LEGO obsession isn’t just nostalgia. With aphantasia, I can’t picture a synth—but I can build one. No mind’s eye, just patterns, logic, and touch. For some of us, imagination clicks into place.
🔗 https://t.co/LX70XOm0vD
@_aphantasia
Agree! To me, AI still feels like magic, but it’s magic I can understand. Maybe that’s because, as a Gen-Xer, I’ve lived through every stage of the digital evolution. From cassettes to Spotify, floppy disks to the cloud, dial-up to 5G…
https://t.co/D3vSVXTBiI