New Year, New Docs In an effort to make LangChain easier-to-use than ever before, we've revamped our docs. Sections include: Getting Started
Modules
[NEW] Use Cases
[NEW] Ecosystem
Gallery
LLMS
-
LangChain Revamps Documentation with New Sections
By
–
-
Prompt Engineering’s Future: From Tricks to Frontier Problems
By
–
Many tasks that require prompt engineering tricks today soon won’t. The scope of “just ask” will increase. But prompt engineering will move on to harder tasks. We won’t run out of problems on the frontier.
-
Happy New Year is All You Need – 2023 Research
By
–
“Happy New Year is All You Need” — Akhaliq et al 2023
-
Prompting GPT-3 with the “Format Trick” for Complex JSON Synthesis
By
–
Prompting GPT-3 using the "format trick" (implemented as a Python function) to synthesize complex example JSON objects, e.g. for mock API responses. Output is shown in second screenshot.
-
AI Model Performance Comparison for Code Generation
By
–
For zero-shot prompts with instructions text-davinci-003 does better in my experience. The text models are actually trained on just as much code as code-davinci-002.
-
Conversational AI Systems: Chatbots, Voice Assistants, Machine Translation
By
–
In this @Cognilytica #AIToday #podcast AI Glossary Series episode 'Conversational Systems, Chatbots, Voice Assistants, Machine Translation' hosts @rschmelzer & @kath0134 define these terms and and explain how they relate to #AI. Full episode: https://
cognilytica.com/2022/12/30/ai-
today-podcast-ai-glossary-series-conversational-systems-chatbots-voice-assistants-machine-translation/?utm_source=dlvr.it&utm_medium=twitter
… #NLP #tech -
Instruction Template Method for Synthesizing Code Files in ChatGPT
By
–
A demo of my "instruction template" method for synthesizing complete code files in ChatGPT. Templates that mix literal code with inline placeholder instructions give better control over generations than using English prose.
-
Chain-of-Thought and Consensus Enhance GPT-3 Problem Solving
By
–
Chain-of-thought allows GPT-3 to solve problems it otherwise cannot solve at all. Consensus allows it to more reliably solve problems it can only solve some of the time. Here, we use both to demonstrate multi-step reasoning and recitation of factual knowledge.
-
Using GPT-3 for a Step-by-Step MD5 Hash Calculation Task
By
–
In the Python script generated by the first instruction template, we give GPT-3 the following prompt: Q: What is the final character of the MD5 hash of the last digit of the release year of the Grimes album "Visions"?
A: Let's think step by step. -
AI Reasoning Technique ‘Let’s Think Step by Step’ Discussed with Research Link
By
–
Next we apply "Let's think step by step," the method developed by Kojima et al. for improving accuracy on deductive reasoning problems. This encourages the model to lay out its reasoning, making it more likely to be right: https://
arxiv.org/abs/2205.11916