Favorites from our prompt engineering tournament
blog.promptlayer.com
Favorites from our prompt engineering tournament
1–10 of 23 posts
Re: Favorites from our prompt engineering tournament
#2I couldn't find any results, just prompts, did I miss something?
Re: Favorites from our prompt engineering tournament
#3Prompt engineering doesn't feel like an activity that creates sustainable AI advancement. A prompt may work well with one model, in most situations, but even the best practices seem too experimental.
For their competition to avoid a PR disaster, isn't it better to look in the model? Perhaps observe the weights, when the AI says something that you want to avoid in the future. A safeguard could trigger if the model is going in that direction.
Re: Favorites from our prompt engineering tournament
#4Prompt engineering doesn't feel like an activity that creates sustainable AI advancement. A prompt may work well with one model, in most situations, but even the best practices seem too experimental. For their competition to avoid a PR disaster, isn't it better to look in the model? Perhaps observe the weights, when the AI says something that you want to avoid in the future. A safeguard could trigger if the model is…
LLM's are trained in much the same way, so while your point stands, most/all of the tips here are going to be useful for LLM's for at least a year or so.
If a tip was like "use XML tags to give clarity to the model," then it wouldn't be sustainable.
Re: Favorites from our prompt engineering tournament
#5Interesting analogue to books like "How to win friends and influence people". This genre of self help books include a lot of things that when you squint look like prompt engineering on humans
Re: Favorites from our prompt engineering tournament
#6Prompt engineering doesn't feel like an activity that creates sustainable AI advancement. A prompt may work well with one model, in most situations, but even the best practices seem too experimental. For their competition to avoid a PR disaster, isn't it better to look in the model? Perhaps observe the weights, when the AI says something that you want to avoid in the future. A safeguard could trigger if the model is…
> Prompt engineering doesn't feel like an activity that creates sustainable AI advancement.
Agreed, it should really be rolled into fine tuning. If you're building a model for PR, for example, it should already be fine tuned so it can't say anything disastrous. Prompt engineering is only really relevant to general-purpose models which aren't that useful to begin with (other than "fun" chatting).
Re: Favorites from our prompt engineering tournament
#7Am I the only one annoyed by the term “prompt engineer{ing}”?
I thought this was a meme, but I have actually seen some job posts for “prompt engineer”.
Re: Favorites from our prompt engineering tournament
#8Last year I’ve seen a live “prompt battle” and it was great: a single-elimination tournament with an applause meter, a hype-man and music!
Re: Favorites from our prompt engineering tournament
#9Am I the only one annoyed by the term “prompt engineer{ing}”? I thought this was a meme, but I have actually seen some job posts for “prompt engineer”.
I get a feeling of incongruity about the term. I think it's because prompts aren't a "system". At least as far as I understand it.
Re: Favorites from our prompt engineering tournament
#10Prompt engineering doesn't feel like an activity that creates sustainable AI advancement. A prompt may work well with one model, in most situations, but even the best practices seem too experimental. For their competition to avoid a PR disaster, isn't it better to look in the model? Perhaps observe the weights, when the AI says something that you want to avoid in the future. A safeguard could trigger if the model is…
> Prompt engineering doesn't feel like an activity that creates sustainable AI advancement.
Chatgpt was created from gpt via prompt engineering? An inverse chatgpt where user answers questions instead of the other way around also has applications.