If you are anything like us, your codebase probably has some prompts in it. What we have observed is that LLMs can auto-improve them significantly. The key insight is that, to go beyond few-shot prompting, a thinking agent can now iteratively evaluate the quality of results, hypothesize improvements, and test them out until converging toward the optimal prompt.
We’ve been using this heavily in our work and have got great results in terms of user satisfaction and the relevance of our system.
I’m sharing here with you the protocol we use: you can just give the link to your coding agent and it will know how to execute it.
Hope this will be useful to at least some of you. And happy to chat about how you are optimizing prompts in your work?
Nice thing to include end-to-end encryption. I am interested to know what users say about it? Is it a key reason in their decision to choose your solution?
As long as we go and just criticize, or say X should not be trasted, I think we are not helping move things forward on the privacy front. It's a good thing that people make tools. Some are OK, some are not doing the job. Eventually, overall, there'll be some progress. At least, there is a discussion and awareness.
Ah, the third leg of the solutions stool: civil, government, and tech. I'd argue any culture will have a mix of all three.
For traffic accidents, there might be various applications of lawsuits, citations, and speed bumps in your town.
In the case of SaaS, we might have only one or two. For example, take LinkedIn last week, selling everyone's PII to ScribD. There might be legal issue in GDPR or CA jurisdictions. There's probably no civil one (?). There is certainly no tech one: you need your PII to be on LI so your friends can find you, because that's the value of LI. I suppose in there future there could be a tech solution here with agents representing you in the cloud, or maybe e2e homomorphic encryption, but it's surely not what drives LI's income at the moment.
We’ve been using this heavily in our work and have got great results in terms of user satisfaction and the relevance of our system.
I’m sharing here with you the protocol we use: you can just give the link to your coding agent and it will know how to execute it.
Hope this will be useful to at least some of you. And happy to chat about how you are optimizing prompts in your work?
reply