Haven’t worked with dspy yet. Do you like it?
@mattshumer_
-
AI System Shows Notable Improvements in Performance Capabilities
By
–
It’s noticeably better, smarter, more thorough and malleable
-
Direct API usage over LLM frameworks for faster development
By
–
The reason I can work so fast is simple: I use no LLM frameworks, just hit the APIs directly for what I need. Frameworks are a time-suck. That, and I use Claude as an engineering assistant. While I’m working on writing a prompt or integrating some code, I’ll simultaneously have
-
Claude 3 Instance Evaluates Multiple Outputs Decision Making
By
–
A separate Claude 3 prompt instance is shown the two outputs, the task description, inputs, etc., and can make a decision from there. Lots of ways to make this more robust.
-
Building AI Tools Efficiently: Prompt Engineering Best Practices
By
–
I actually spend way less time on things like this than you might think! The whole claude-prompt-engineer buildout took less than 30 minutes last night. Did it while cooking dinner. After building with AI for a while, it becomes second nature 🙂
-
Making Individual Prompt Development Accessible and Measurable
By
–
Not exactly haha. I just want to make the development of individual prompts more accessible and measurable. The real work is stringing these prompts together to make a system like this one.
-
Combining Chamath’s insights with Groq Inc technology
By
–
Thanks for sharing this Chamath. I guess I'll have to combine this with @GroqInc at some point 🙂
-
Using Older GPT-4 Versions as Alternative Solution
By
–
Yeah, but you can always use the old GPT-4 version!
-
AI-Generated Prompts Outperform Manual Prompt Engineering
By
–
I've been blown away by the quality of the generated prompts. Often, they outperform the prompts I'd write by hand (especially when I ask it to generate and compare 10+ prompts). I am already using this for my day-to-day prompting work… it takes the guesswork out of it.
-
Prompt Engineering Tournament System with ELO Comparison
By
–
How it works, in a nutshell:
– The user describes the task and input variables
– Claude generates many candidate prompts to try
– Each prompt generates against each test case, and the outputs are compared (by Claude!) for each combo, ELO tournament-style
– Highest score wins!