Another great walk through from @CobusGreylingZA Tree of though has a lot going on under the hood – nice to be able to see all of that with langsmith
PROMPT ENGINEERING
-
Superagent Prompt Tops LangChain Hub Platform
By
–
The top prompt on the LangChain Hub is a Superagent prompt This prompt helps to power one of the leading agent platforms Explore the prompt here: https://
smith.langchain.com/hub/homanp/sup
eragent
… And join @pelaseyed and I to discuss all things superagent related this Thursday https://
crowdcast.io/c/ltmfb7aqb3ho -
LangChain Hub: Behind-the-Scenes Prompts for Content Generation
By
–
This is fantastic!!
— Harrison Chase (@hwchase17) 13 septembre 2023
Also really cool to look at the prompts that are doing behind the scenes – all on the hub
Blog generator: https://t.co/0sCjYbjOjW
Tweet-from-text: https://t.co/ncILBMPzsg
Newsletter: https://t.co/PkfUwRfSjY
Summarize: https://t.co/4OUXh2lpey https://t.co/jqRGSSfBblThis is fantastic!! Also really cool to look at the prompts that are doing behind the scenes – all on the hub Blog generator: https://
smith.langchain.com/hub/hardkothar
i/blog-generator
… Tweet-from-text: https://
smith.langchain.com/hub/hardkothar
i/tweet-from-text
… Newsletter: https://
smith.langchain.com/hub/hardkothar
i/newsletter_generator
… Summarize: https://
smith.langchain.com/hub/hardkothar
i/text_summary
… -
Optimizing OSS Models with System Prompts RAG Fine-tuning
By
–
We use established fast and simple techniques to improve OSS model performance. These techniques include system prompts to generate less verbose answers, RAG to reduce hallucinations and fine-tuning to improve accuracy. (7/10)
-
ToolBench: Comprehensive AI Agent Orchestration Benchmark Suite
By
–
We create a comprehensive benchmark suite that covers a range of use cases. Using a single API call to do something useful to orchestrating and planning multiple API calls to solve a complex problem. The benchmark is called ToolBench, available at https://
github.com/sambanova/tool
bench
… (4/10) -
Teaching LLMs to Use Tools Over Direct Computation
By
–
For example, it's better to teach a LLM to use a calculator rather than teaching it to do complex math. (2/10)
-
Custom Instructions for ChatGPT: Optimizing Language Model Interactions
By
–
Custom instructions for ChatGPT https://
bit.ly/3OFo61m #AI #MachineLearning #DeepLearning #LLMs #DataScience -
ChatGPT as Business Analyst: 5 Ready-to-Use Prompts
By
–
Convierte a ChatGPT en tu analista de negocio [5 prompts listos para usar] #podcast #negocios https://
podcasters.spotify.com/pod/show/negoc
ios-en-crecimiento/episodes/Convierte-a-ChatGPT-en-tu-analista-de-negocio-5-prompts-listos-para-usar-e297cfm
… -
WeChat Chat Loader for Voice-Based Model Fine-Tuning
By
–
Anyone want to help add a wechat chat loader to help finetune models to talk in your voice?