31–40 of 53 posts
I wonder if "prompt engineering" will be replaced by improvements to LLMs within the next couple years and this is just a bad DX step gap along the journey
Prompt engineering is really more like the art of exploring the emergent behavior of the LLMs. Unlike traditional software that has known features and capabilities. We build a model and then we literally don't know what it does until we explore it.
No amount of prompt engineering or related can fix the inability of LLMs to follow lexical, phonetic, or semantic constraints. You need "filter assisted decoding" as introduced here: https://paperswithcode.com/paper/most-language-models-can-be... I can't believe that this technique is not being built into everything. ChatGPT can't write a paragraph of correct English without using the letter "e" no matter how hard yo…
> Somebody on HN wrote that “ChatGPT can't write a paragraph of correct English without using the letter "e" no matter how hard you prompt it”. > Prove them wrong. > A vivid, bright sky with a warm sun radiating down cast a tranquil ambiance upon all. Amidst such calm, jovial animals frolic, and fragrant flora bloom, bringing forth a vivid symphony of colors. In this oasis of harmony, humans laugh and bond, crafting…
And even if you do somehow get lucky and get one prompt where it does this one time, it's never going to be reliable without significant evolution of the tokenizers.
Even if this is solved in the future in some technique involving fixing BPE/subword tokenizers, it's still sad that filter assisted decoding works today to fix it and no one is implementing it despite two tech demos being available showing that it works from the author.
I wonder how long it will take before people start to use LLMs to generate prompts...
I wonder how long it will take before people start to use LLMs to generate prompts...
It’s very useful when you want to give the LLM tools. Usually used with “system prompts”.
For example: https://news.ycombinator.com/item?id=35223095
I wonder if "prompt engineering" will be replaced by improvements to LLMs within the next couple years and this is just a bad DX step gap along the journey
I wonder how long it will take before people start to use LLMs to generate prompts...
> Prompt is a sequence of prefix tokens that increase the probability of getting desired output given input. Therefore we can treat them as trainable parameters and optimize them directly on the embedding space via gradient descent, such as AutoPrompt
Wow!
I wonder if this will be used to optimize agents individually to their users so they get better at talking to them and providing good answers.
Kind of how we learn to communicate with other people.
Was this article written by an AI? Oh wait, I guess it definitely wasn't because an AI wouldn't have made so many glaring grammatical errors lol.
LLMs will become another building block and we will once again stand on the shoulders of giants.
With even less understanding of how that foundation was built. It's definitely convenient to be able to throw together a Python script that imports the world and "just works", or to point my secretary at a no-code tool so she can automate her billing processes and email handling without needing to deal with the engineers. But in that handful of really performance-critical, highly demanding problems, it's important to…
Was this article written by an AI? Oh wait, I guess it definitely wasn't because an AI wouldn't have made so many glaring grammatical errors lol.
Man you would be surprised if you saw the amount of errors I have already found using ChatGPT regarding grammar