I’m using @Lutra_AI for email drafting. You could give it more context by asking it to draft based on say instructions from a Google doc, and also find recent emails from that sender
PROMPT ENGINEERING
-
Two-Stepping: A Technique to Improve AI Prompt Results
By
–
If your prompts aren’t quite giving you the results you want, here’s something to try. I call it "two-stepping". The key here is to get the AI to output something bad before it outputs something good. Here's how two-stepping works: First, prompt the AI with your initial
-
Mitigations Against Prompt Injection Attacks
By
–
What mitigations do you have in place against prompt injection attacks?
-
What Prompts Do You Use for Relevance Judgements?
By
–
What kind of prompts do you use for relevance judgements?
-
Balancing Cost and Performance in Model Selection
By
–
It's pretty much for when I want it as fast and cheap as possible but I can't quite get the results I need from the least expensive model
-
Setting up proper evaluations for AI model selection
By
–
Yet another case where I really need to setup proper evals for my projects so I can get to a definitive answer about which models are "good enough" for what I'm trying to do
-
HireBorderless RAG-Powered Legal AI Assistant with Cohere
By
–
Learn about the @hireborderless success story in our upcoming webinar on April 30 at 2pm ET! Discover how RAG technology within Cohere’s Command R and Embed model helped them develop a cutting-edge legal AI assistant for global employment. Register here: https://
info.cohere.ai/building-a-rag
-powered-ai-legal-assistant-with-cohere
… -
Session Timeouts and AI Collaboration Experience with Claude
By
–
i took a few days off the karpathy task to handle other matters but also its kinda annoying to restart sessions after the 24hr timeouts. i just love love love the experience of chatting with it to figure out its plan. its not perfect but when i just INSIST it does what i tell it
-
Mitigating Prompt Injection: Disable Markdown Images and Links
By
–
While prompt injection remains unsolved, for this particular issue there is a known mitigation: don't ever support markdown (or HTML) images that load images from domains you do not control! More painful but also necessary: don't support outbound clickable links either
-
RAG Security: Prompt Injection Risks in Untrusted Data Processing
By
–
Yet another example illustrating an inconvenient truth: If you build a RAG system that can be used to process data from untrusted sources, and you include the ability to embed images from or links to external domains, then you're going to have prompt injection exfiltration holes