I found this amazing. Code Integrity+Code generation is what we need at this moment. Fed up of having AI tools generating code that is not logically correct or not passes test cases. Future is amazing.
LLMS
-
New LLMOps Short Course by Google Cloud
By
–
New short course on LLMOps!
— Andrew Ng (@AndrewYNg) 18 janvier 2024
LLMOps (large language model operations) is a rapidly developing field that takes ideas from MLOps (machine learning operations) and specializes them to building and deploying LLM-based applications. In this course, taught by @googlecloud's Erwin… pic.twitter.com/zTKXFHSlBZNew short course on LLMOps! LLMOps (large language model operations) is a rapidly developing field that takes ideas from MLOps (machine learning operations) and specializes them to building and deploying LLM-based applications. In this course, taught by @googlecloud
's Erwin -
Hermes and LLaVA Enable Vision Capabilities for AI
By
–
Yeah you can use Hermes with vision by @teknium or LLaVA
-
Full prompt engineering guide from OpenAI
By
–
Here's the full prompt engineering guide if you want to explore it in more detail: https://
platform.openai.com/docs/guides/pr
ompt-engineering/strategy-test-changes-systematically
… -
Systematic testing and evaluation of ChatGPT outputs
By
–
Strategy 6: Systematically Test and Evaluate ChatGPT Outputs. Examples:
– Implement a model-based evaluation: check if ChatGPT's answers include specific known facts.
– Use a systematic approach: restate the fact, find the closest citation in ChatGPT's answer, and judge its -
Strategy 5: Use External Tools for Knowledge Retrieval
By
–
Strategy 5: Use External Tools. Examples:
– Implement embeddings-based search for knowledge retrieval.
– Use code execution for accurate calculations or API calls.
– Provide ChatGPT access to specific functions. -
Strategy 4: Give the Model Time to Think
By
–
Strategy 4: Give the Model Time to 'Think'. Examples:
– Instruct ChatGPT to develop a solution before concluding.
– Use inner monologue or queries sequence to aid reasoning.
– Ask ChatGPT to review previous responses for completeness. -
Strategy 3: Split Complex Tasks into Simpler Subtasks
By
–
Strategy 3: Split Complex Tasks into Simpler Subtasks. Examples:
– Use intent classification for relevant instructions.
– For long dialogues, summarize or filter past conversation.
– Summarize long documents piece by piece and build a full summary. -
Strategy 2: Provide Reference Text for ChatGPT Answers
By
–
Strategy 2: Provide Reference Text. Examples:
– Instruct ChatGPT to use reference text for answers.
– Direct ChatGPT to answer with citations from reference text. -
OpenAI’s Free Prompt Engineering Guide: 6 Essential Strategies
By
–
OpenAI has released a free guide for prompt engineering. No payment required! Here's 6 essential strategies for writing the most effective prompts for ChatGPT