91–94 of 94 posts
Very cool! But for hard enough problems, prompt engineering is kind of like hyperparameter tuning. It's only a final (and relatively minor) step after building up an effective architecture and getting its modules to work together. DSP provides a high-level abstraction for building these architectures—with LMs and search. And it gets the modules working together on your behalf (e.g., it annotates few-shot demonstratio…
Earlier quoted context omitted.
For the financial applications at finclout I would prefer engineer. Yet for the stable diffusion tasks, I'd prefer designer.
Is your website https://finclout.io/ ? Some very odd behaviour in the animations on the page when you load it (Chrome 109.0.5414.119 on Mac) that you might want to have someone look at.
Very cool! But for hard enough problems, prompt engineering is kind of like hyperparameter tuning. It's only a final (and relatively minor) step after building up an effective architecture and getting its modules to work together. DSP provides a high-level abstraction for building these architectures—with LMs and search. And it gets the modules working together on your behalf (e.g., it annotates few-shot demonstratio…
Interesting. It's almost the exact same structure (although better organized) that I have built in my "AI Programmer" project (also in Node). Which by the way I hope to have a new release within a week or so. I am not mentioning the domain name again until I have the new release because it much, much better than the version I have up now. The core idea is that you need a certain structure in order to deal with the li…
>so you will need to truncate the beginning of the conversation at some point I wrote a little python script to keep track of a running conversation when I started playing with openai's completions API. I keep track of how many tokens the prompt is taking up, and when it gets too close to some configurable threshold, I then have a different prompt to tell the AI to summarize the conversation and any previous summary,…
If you don't mind sharing the code I'd be super interested to see how it works