I'll probably get flamed for this, but I like gpt-4.5. Although I'll tell you what. It's a lot easier to like when it's "free" inside your ChatGPT Pro plan. If I was paying per-token I'd be afraid to experiment with it and learn how it works.
PROMPT ENGINEERING
-
When does the AI-as-intern analogy fail us?
By
–
We keep saying AI is like a very smart intern: give it more background & context, show it good examples, review its work, assume it has low expertise, assume it won’t be perfect. When is this analogy shooting us in the foot?
-
Full GPT-4.5 test: how to use it and what for?
By
–
I just spent the whole day (and a bit of the night) on #GPT4_5 Here is my full test → https://youtu.be/Sf8-3JnWX7Q So what is this new AI on #ChatGPT worth? How to use it properly? What for? I show you EVERYTHING!
-
Dynamic AI UI Adapts Commands in Real-Time
By
–
Redefining AI Interaction! 🚀
— Pascal Bornet (@pascal_bornet) 28 février 2025
Coder Ronith Kandallu has created a dynamic prompt field—an AI-powered UI that intelligently adapts commands in real-time based on what you type. This innovation makes interacting with AI more seamless, intuitive, and powerful than ever! 🔥
💡 A… pic.twitter.com/lSyNXmKZZ3Redefining AI Interaction! Coder Ronith Kandallu has created a dynamic prompt field—an AI-powered UI that intelligently adapts commands in real-time based on what you type. This innovation makes interacting with AI more seamless, intuitive, and powerful than ever! A
-
Crashing Grok 3 by prompting a new efficient language
By
–
Looks like I crashed Grok 3 by prompting it to: 1. Come up with an entirely new, extremely efficient language for writing and speaking. 2. Naming this animal in said language.
-
How I Use LLMs: Practical Guide to the LLM Ecosystem
By
–
New 2h11m YouTube video: How I Use LLMs This video continues my general audience series. The last one focused on how LLMs are trained, so I wanted to follow up with a more practical guide of the entire LLM ecosystem, including lots of examples of use in my own life. Chapters
-
GPT-4.5 Solves Hexagon Ball Challenge with Creative Prompting
By
–
Forget fancy benchmarks, this is the real eval!
— Romain Huet (@romainhuet) 27 février 2025
GPT-4.5 just nailed the “ball bouncing in a spinning hexagon” challenge in one shot—@edwinarbus simply asked it to be more creative! ⬡✨ https://t.co/I8tF6m2X14Forget fancy benchmarks, this is the real eval! GPT-4.5 just nailed the “ball bouncing in a spinning hexagon” challenge in one shot—
@edwinarbus simply asked it to be more creative! ⬡ -
Understanding Value and Interactions Enabled by Sampling
By
–
I don’t fully understand the value/unlock of sampling, to be honest. What are the types of interactions you think it can enable that I’m not appreciating?
-
GPT-4.5 Early Testing Shows Natural Interaction and Broader Knowledge
By
–
Early testing shows that interacting with GPT-4.5 feels more natural. Its broader knowledge base, improved ability to follow user intent, and greater “EQ” make it useful for tasks like improving writing, programming, and solving practical problems.
-
GPT-4.5 Announcement Blog Post
By
–
Blog post is out as well https://
openai.com/index/introduc
ing-gpt-4-5/
…