Skip to main content

Paweł Huryn, Kent Beck, and Ben Lang posted new notes

 
Substack

Paweł Huryn, Kent Beck, and Ben Lang posted new notes

We have a new king of building AI agents: GPT-5. I spent an entire evening comparing it with other models. My previous benchmark turned out to be too easy. Over 10 runs, GPT-5 didn’t fail even once 🤯 Let’s break it down: ‎ The task assigned to agents: Create a new list inside Kanban board Search the web to find the recent news about Amazon Add all the search results to the list ‎ Completing the task required: Preparing a simple plan Using multiple tools in the right order…
Read More
1941
Wow! Codex with ChatGPT-5 is SO WORDY. It’s…
Read More
62
New next play guest post…
Read More
10 1
064
 

Comments

Popular posts from this blog

Confirm your subscription

Don't miss a thing Confirm your subscription Hi there, Thanks for subscribing to f‍i‍t‍g‍i‍r‍l‍-‍r‍e‍p‍a‍c‍k‍s‍.‍s‍i‍t‍e! To get you up and running, please confirm your email address by clicking below. This will set you up with a WordPress.com account you can use to manage your subscription preferences. By clicking "confirm email," you agree to the Terms of Service and have read the Privacy Policy . Confirm email ...

Welcome to Coding Challenges!

You're the latest member of the Coding Challenges newsletter. ͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏     ­͏   ...

Welcome To My Blog

Hello All Welcome to my blog. I am going to share what I learnt in the technology & life lessons in this blog. This blog mainly contains the projects I created & Observations I felt in my life.