Monitoring a model’s chain-of-thought is far more effective than watching only its actions or final answers. The more a model “thinks” (longer CoTs), the easier it is to spot issues.
PROMPT ENGINEERING
-
OpenAI Model Spec: Intended Behavior for AI Models
By
–
The Model Spec — intended behavior for the models that power OpenAI’s products:
-
GPT-5.2-Codex: Advanced Model for Long-Horizon Agentic Coding
By
–
Just launched GPT-5.2-Codex! The best model for long-horizon agentic coding, including strong performance on refactors and migrations. Codex becoming very magical.
-
Build Apps Instantly with ChatGPT and Replit Integration
By
–
Turn your ideas into apps right from ChatGPT using Replit!
— Sumanth (@Sumanth_077) 18 décembre 2025
Here’s how it works:
1. Connect Replit app to ChatGPT
2. Describe your app idea in ChatGPT and tag Replit to build
3. Preview your app and iterate instantly in ChatGPT https://t.co/XObDx2g640Turn your ideas into apps right from ChatGPT using Replit! Here’s how it works: 1. Connect Replit app to ChatGPT 2. Describe your app idea in ChatGPT and tag Replit to build
3. Preview your app and iterate instantly in ChatGPT -
Genspark CEO says ‘just prompt it’ – Microsoft Office in trouble
By
–
Genspark's CEO says "just prompt it."
— Robert Scoble (@Scobleizer) 18 décembre 2025
My reaction? Microsoft Office is in trouble as more people discover the new way to work. They won't be going back. https://t.co/cMltEAB9Q6Genspark's CEO says "just prompt it." My reaction? Microsoft Office is in trouble as more people discover the new way to work. They won't be going back.
-
Managing Deepagents Memory: Learning and Reflection Over Time
By
–
Managing Deepagents Memory Memory allows agents to learn tasks, knowledge, or preferences over time. Here, we overview two ways to update Deepagent-CLI memory: direct instruction and reflection over past Deepagent sessions. : https://
youtu.be/3aS1A-0775s -
New LangChain Academy Course: Building Agents with Python
By
–
🔗 New LangChain Academy Course: Introduction to LangChain (Python) 🔗
— LangChain (@LangChain) 18 décembre 2025
Learn how to build with LangChain – our open source framework that makes it easy to start building agents with any model provider.
In this course, you’ll create agents that can reason, use tools, and take… pic.twitter.com/ixcarxVJ1BNew LangChain Academy Course: Introduction to LangChain (Python) Learn how to build with LangChain – our open source framework that makes it easy to start building agents with any model provider. In this course, you’ll create agents that can reason, use tools, and take
-
Nano Banana Pro: Image Generation and AI Scam Trends 2026
By
–
Nano Banana Pro remains my favorite image generation model. Undoubtedly, 2026 will see more AI scams. And more revenue-generating AI influencers. Prompt: This woman is sitting on a white beanbag and laughing. She’s wearing a light pink cap, a black high necked crop top, and
-
Accounting for AI Model Quirks Improves Real-World Performance
By
–
Designing ways to account for the quirks of AI models’ behavior is becoming ever-more important: as the models’ capabilities on real-world tasks get better, there’ll be a lot of value in setting them up for success.
-
Optimizing ChatGPT Custom Instructions for Maximum Usefulness
By
–
I want my ChatGPT to be very useful for me, so over time, this is how I optimized the custom instructions: Be extremely accurate. Be brutally honest and call out misconceptions. No sycophancy. Tell me when I'm wrong. Think from first principles. Be encouraging. Take a