Agentic AI = AI that plans + uses tools + remembers + collaborates + executes. This cheat sheet nails the core stack: Planning | Memory | Tool use | Multi-agent collab | Execution frameworks like LangChain, CrewAI, AutoGen. Agents are how GenAI turns into
LLMS
-
LLMs as Skinnerian, Popperian, and Gregorian Creatures: Cognitive Limitations
By
–
Reflection on @dwarkesh_sp
's reflections on his interview with Rich Sutton, and why LLMs are exciting because they are Skinnerian, Popperian and Gregorian creatures. Minds with finite capacity cannot adapt forever without having to forget previous knowledge. This is true of -
Cloning Brain into AI Gives 5 Hours Daily Efficiency
By
–
I've cloned my brain into an AI. (This isn't a joke ) I didn't just give it a prompt. I gave it my personal "Bible": My 2026 goals My writing style My work methods Here's how I gain 5h/day →
-

First LLM Contact from Space Using Open Source Gemma Models
By
–
First LLM contact from space using our highly efficient open source Gemma models! Huge congrats to @PhilipJohnston and the @starcloud_ team!
-
Abacus AI Desktop Offers Top Coding Models Including Sonnet 4.5
By
–
Access all the top coding models, including Sonnet, Opus, GPT 5.2 and Gemini, on Abacus AI Desktop. Our default is Sonnet 4.5, which we believe strikes the right balance between cost and performance. We are on top of terminal bench #1 and plan to soon be on top of terminal
-
GPT-5.2 Thinking vs Pro Model Review Comparison
By
–
My review for GPT-5.2 Thinking (not Pro) was not as positive. Pro, however, is an amazing model, which is why I say so.
-

GPT-5.2 aces AIME math without tools
By
–
GPT-5.2 Thinking scored 100% on AIME (math without tools) Pretty good progress
-

OpenAI Launches GPT-5.2 Family Advanced Model Professional
By
–
The GPT 5.2 family is now on Poe! The GPT‑5.2 family is OpenAI’s most advanced model for professional work and long‑running agents. It comes with big gains in reasoning, long‑context, tool use, vision, and coding. (1/2)
-
GPT-5.2 Now Available on Poe App and API
By
–
You can try it in the Poe app on all platforms and in the Poe API at: https://
poe.com/GPT-5.2, https://
poe.com/GPT-5.2-Chat, and https://
poe.com/GPT-5.2-Pro. (2/2) -
GPT-5.2 Thinking vs Opus Pro: Model Comparison and Daily Usage
By
–
Please read the content of the review. I make it clear that GPT-5.2 Thinking is an incredible model, but I barely use it day-to-day, as Opus + Pro fit what I need much better, and speed lines up.
