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
LLMS
-
Self Learning GPTs: Improving Applications Through User Feedback
By
–
Self Learning GPTs: Using Feedback to Improve Your Application We built and hosted a simple demo app to show how applications can learn and improve from feedback over time: …
https://self-
learning-gpts-vz4y4ooboq-uw.a.run.app The app is called "Self Learning GPTs" and it uses LangSmith to gather feedback -
Bay Area Event: Open-Source LLM Frameworks and Production Apps
By
–
Bay Area Friends: Join us Apr 4th to learn about the lastest open-source #LLM frameworks and tips for building #production-grade apps from the leaders at @predibase @llama_index
, @tryolabs and @guardrails_ai
! Save your spot and invite your friends! https://
pbase.ai/4am4ys9 -
Discussion on LLM system prompts and memory feature availability
By
–
Nice guide! It works for enabling a Personalization tab in settings but not an ability to save memories unfortunately. I feel like it depends on another A/B testing cohort which defines which system prompt you will interact with. For example, I don’t have “bio” feature in
-
Using Older GPT-4 Versions as Alternative Solution
By
–
Yeah, but you can always use the old GPT-4 version!
-
Claude 3 Prompt Engineer Auto-generates Test Cases
By
–
It's based on my previous `gpt-prompt-engineer` that went viral (5k+ stars on Github) with a few massive improvements:
– Uses Claude 3 (writes far better prompts than GPT-4)
– Auto-generates test cases, further automating the prompt eng process
– Supports multi-variable prompts! -
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! -
Claude Constrained Agent Chains Calls for Optimal Prompts
By
–
`claude-prompt-engineer` is a constrained agent — meaning its behavior is highly-controlled, leading to better results than open-ended agents. It chains together lots of Claude 3 calls that work together to find the best possible prompt.
-
MistralAI Function Calling Support and Claude Bedrock Integration
By
–
MistralAI Function Calling is now officially supported on v1.6.2 Along with other updates: Claude 3 Haiku support on Amazon Bedrock Azure OpenAI Vision Patch note:
-
Specifying Tools for Mistral Models: Payment Functions
By
–
1/ Specify tools We need 2 tools in this example: retrieve_payment_status retrieve_payment_date In order for Mistral models to understand the functions, for each tool, we need to describe the tool's name, description, parameters, and the function.