I have tools for that, but for tasks i do there’s no “improve prompt”, only for some, and anyway I’m working on a custom prompt tool that i think is better because static prompts that are premade cannot be “improved “ without knowing users goal!
PROMPT ENGINEERING
-
Claude 3.5 Sonnet Shows Robustness in Complex Tasks
By
–
One huge change I'm seeing in the new Claude 3.5 Sonnet model…it's more robust. I'm chucking complex decisions and code at it, and for each prompt, it's not only giving me "standard" output, it's giving flags, considerations, next steps, and alt decisions unprompted. LOVE.
-
Agent Design with Fast Inference for Automation and Accuracy
By
–
🙏 Thanks to @chamii22 from @NumbersStnAI for showcasing how they are designing their Agents in our latest Webinar.
— SambaNova (@SambaNovaAI) 23 octobre 2024
Automation + Fast Inference is absolutely critical to correct errors & provide higher accuracy responses to end users. ✅ pic.twitter.com/bd2V0khbGoThanks to @chamii22 from @NumbersStnAI for showcasing how they are designing their Agents in our latest Webinar. Automation + Fast Inference is absolutely critical to correct errors & provide higher accuracy responses to end users.
-
AI Consistency: Same Answer to Equivalent Questions
By
–
No, but an AI should give the same answer to questions with a single correct answer if the question is asked in two different ways. The words can be different, but the information should be the same.
-
Building AI-Powered Inspirational Quote Screensaver with Claude
By
–
Has anyone created an Instagram page with AI inspirational quotes yet? I'm tempted to build a screensaver that shows a new hilarious quote each day. Claude is on fire with these
-
LangSmith Adds Side-by-Side Trace Comparison with Prompt Highlighting
By
–
no more opening up two LangSmith windows side by side!
— Harrison Chase (@hwchase17) 23 octobre 2024
easily compare traces to see where the differ… including some nice highlighting of prompt differences https://t.co/xSbh7J4k4Wno more opening up two LangSmith windows side by side! easily compare traces to see where the differ… including some nice highlighting of prompt differences
-
10 Best GPTs to Automate Tedious Work
By
–
I don't get why most people don't use GPTs inside ChatGPT. Let me show you 10 of the best GPTs that'll help you automate your tedious work:
-
Optimizing Tool Retrieval in RAG Systems: A Balanced Approach
By
–
Optimizing Tool Retrieval in RAG Systems: A Balanced Approach – http://
jxnl.co https://
bit.ly/3Bpr4UX
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Perplexity Launches Reasoning Mode for Advanced Search
By
–
Pro Search is now more powerful. Introducing Reasoning Mode!
— Perplexity (@perplexity_ai) 22 octobre 2024
Challenge your own curiosity. Ask multi-layered questions. Perplexity will adapt.
Try it yourself (sample queries in thread)👇 pic.twitter.com/NHlxA34nLdPro Search is now more powerful. Introducing Reasoning Mode! Challenge your own curiosity. Ask multi-layered questions. Perplexity will adapt. Try it yourself (sample queries in thread)