3/ Typewriter results None of the agents are perfect. GPT-4 had a hard time typing "keyboard" and "head" https://
smith.langchain.com/public/ff14ecb
2-3664-4c4a-b2dc-d8aa9fd2185d/d
…
PROMPT ENGINEERING
-
GPT-4 Typewriter Task Performance Evaluation and Limitations
By
–
-
GPT-4 Turbo JSON Mode for Valid Model Responses
By
–
With GPT-4 Turbo, we’ve introduced JSON Mode, which ensures model responses are all valid JSON objects. Is this what you’re looking for, or is there something more specific you need? Thanks! https://
platform.openai.com/docs/guides/te
xt-generation/json-mode
… -
API Improvements and Code Interpreter Tool Configuration Feedback
By
–
Thanks for your insights, Mckay! We’ll look into more granular controls for API keys and request cost clarity. Super helpful feedback on the Assistants and DALL·E APIs too. On Code Interpreter, any specific tool configurations you’d like to see?
-
Documentation priorities for model changes and updates feedback
By
–
Thanks for the feedback! Regarding docs on model changes, what’s most important to you? Grasping differences between models for your prompts, comparing model performances with evals, or getting clearer updates on upgrades and timelines?
-
Placebo Effect on Large Language Models Explained
By
–
placebo for humans
> "this pill will make you smarter" placebo for llms
> "you are the best software engineer" -
Advanced RAG Applications with LangChain, Llama Index, Deep Memory
By
–
We go beyond basic RAG applications, equipping you with the skills to create more complex, reliable products with tools like @langchain
, @llama_index (with insights from @jerryjliu0
), and Deep Memory. Whether you're a beginner or professional, join us to elevate your AI skills! -
Claude Messages API Helps Developers Catch Errors Early
By
–
Our new Messages API helps developers catch errors early, especially when constructing prompts, so they can get the best outputs from Claude. This includes support for text-in-text-out, streaming and pre-filled Assistant text, as well as our Python and TypeScript SDKs.
-
Jerry Liu on AI Future: LlamaIndex, RAG, and LLM Solutions
By
–
@jerryjliu0 on the Future of AI: @llama_index, LLMs, RAG, Prompting and more!
— Louis-François Bouchard 🎥🤖 (@Whats_AI) 19 décembre 2023
In this 25th episode, Jerry, co-founder and CEO of LlamaIndex shares valuable insights for anyone implementing LLM solutions. I decided to focus on Retrieval Augmented Generation (RAG) since it is the… pic.twitter.com/oIDkeSUsJ7@jerryjliu0 on the Future of AI: @llama_index
, LLMs, RAG, Prompting and more! In this 25th episode, Jerry, co-founder and CEO of LlamaIndex shares valuable insights for anyone implementing LLM solutions. I decided to focus on Retrieval Augmented Generation (RAG) since it is the -
Low-Resource Languages Enable GPT-4 Jailbreak Research
By
–
Exciting news from #NeurIPS2023! The "Low-Resource Languages Jailbreak GPT-4" paper by Zheng-Xin Yong, Cristina Menghini, and @stevebach from the Snorkel Research team has won the Best Paper Award in the Socially Responsible Language Modelling Research (SoLaR) 2023 Workshop!
-
Quick AI Upscaling: Optimal Creativity and Resemblance Settings
By
–
For quick upscales I'm using: creativity: 3
resemblance: -2
no prompt