Books and notes are RAG for humans.
PROMPT ENGINEERING
-
PhotoAI Enables Extreme Closeups with Improved Prompt Engineering
By
–
Also enabled extreme closeups on http://
photoai.com now Just add "close up of" in front of your prompt and your AI camera will get closer to your AI model Teeth are a bit weird sometimes, working on improving Before this didn't work well because any upscaler -
Using Strict Guidelines to Get Better AI Results
By
–
Getting strict with your AI doesn't make you a bad person. It makes you a smart one. Most of my ChatGPT and Claude prompts do this with a "Disallowed / Prohibited" section. Here's how it works: Especially with complex prompts, sometimes the model will return results that are
-
Advantages of letting AI produce longer, self-evaluated responses
By
–
Yes because you can let it talk longer, consider multiple options, self-evaluate, etc. without a wall of text flooding your screen every time. There are more opportunities for it to usefully babble on when you don’t have to read any of it, even to fish out the answer.
-
Audio Generation vs Multimodal Retrieval: Critical Analysis
By
–
Por cierto. Este ejemplo de generación de audio hay que ponerlo en duda hasta tener más detalles, porque el prompt es "play the sound" y eso podría ser que la IA pudiera buscar de un listado de audios el que responda a esa petición. No sería generación sino retrieval multimodal.
-
Prompt technique: hiding chain-of-thought in code comments
By
–
Teaching ChatGPT to “think silently” by hiding planning, chain-of-thought, or other intermediate writing in interpreted Python code blocks as comments or strings. Text remains visible to the model (and the user, by clicking to view code) without cluttering the chat dialog.
-
Using ‘You are GPT-4o’ as a ChatGPT memory prompt
By
–
Adding “You are GPT-4o” to my ChatGPT memory like it’s a Memento chest tattoo
-
GPQA High Variance Issues and Evaluation Methodology Discussion
By
–
I believe we're running 4 repeats and taking the average, and also using the same zero-shot CoT prompt as before, see https://
github.com/openai/simple-
evals
… But i totally agree with you that GPQA is high variance, I wish there were like 3k examples instead of 300 -
Testing Multimodal AI: Sarcasm, Interruption, McGurk Effect
By
–
I would want to test these multimodal things:
– Sarcasm, watching the face and listening to the voice at the same time "oh yeah that's amazing" – Prompting it to avoid interrupting you: "if I look like I'm still thinking about what to say, don't interrupt me"
– McGurk effect -
ChatGPT 4o can describe images of real people
By
–
New ChatGPT 4o can now describe images of real people, like this one of Barack Obama racing Lightning McQueen in his Mercedes Benz while smoking a cigar, listening to Playboi Carti, getting blocked on X by Paul Skallas, and running over Charli XCX: