This is going to sound like a joke, but it isn't. Machine learning models like ChatGPT benefit from positive reinforcement. It helps them learn when their responses are accurate and effective. So say THANK YOU to your favorite bot. You're helping it get a little smarter.
PROMPT ENGINEERING
-
Mid-U Guidance: Fast Classifier Guidance for Latent Diffusion
By
–
Check out this powerful new diffusion inference technique from @johnowhitaker – 'Mid-U Guidance': Fast Classifier Guidance for Latent Diffusion Models. It lets you very flexible push your generated images towards almost any concept you can imagine.
-
AI-Generated Text Detection and GPT-3 Output Distinguishability
By
–
Lo dicho antes. Y además no creo que esto se consiga por pedirle a la IA que lo haga "para evitar ser detectado". Simplemente creo que cualquier generación que se aleje un poco de la distribución "normal" de escritura de GPT-3, ya será indetectable.
-
Instruction-tuned Models vs Creativity: When Older Models Excel
By
–
I love OpenAIs instruction-tuned models. They make it so easy to get what you want, quickly. But sometimes their outputs are just too “down the middle”. For some applications where creativity is key, older, non-instruction-tuned models can actually perform far better.
-
text-davinci-003 struggles with generic tweet generation
By
–
To get a sense of what I mean, try writing tweets with text-davinci-003. It’s remarkably difficult to get it to generate something that isn’t super generic, even with extensive prompting.
-
Prompt Engineering’s Infancy: A Call for Advanced Tools and Syntax
By
–
Prompt engineering is in its infancy. We still prompt without syntax highlighting, like we’re stuck on POSIX vi. We have no linters, no type-checkers, no macros, no compilers, no syntax even for comments. There is room to grow.
-
Prompt Engineering as Future Career: 20K Views Success
By
–
Last year, I penned my thoughts on How Prompt Engineering will be the career of Future! Glad to see it becoming my first ever medium blog to have crossed 20k views and cited 100+ times in various reputable publications!
-
GPT-3 Enables Declarative Prolog-like Semantics for Programming Languages
By
–
The most magical thing to me about programming languages in GPT-3 is that, if you set it up right, almost *any* language can be used with declarative, Prolog-like semantics:
-
Midjourney Course Advances: Complete Knowledge Thread
By
–
EL CURSO DE MIDJOURNEY AVANZA Todo el conocimiento que un humano puede poseer sobre Midjourney estará en este gran hilo que poco a poco se va actualizando. Ya vamos por la página #54
-
Spectacular AI-Generated Image with Prompt Included
By
–
#54 ¡SUFICIENTE COMIDA POR HOY! Vamos a parar aquí hoy con otra espectacular imagen de @LinusEkenstam y su prompt incluido!