https://
hyperwriteai.com/personal-assis
tant
… https://
chrome.google.com/webstore/detai
l/hyperwrite-ai-assistant/kljjoeapehcmaphfcjkmbhkinoaopdnd
…
PROMPT ENGINEERING
-
Hyperwrite AI Personal Assistant Chrome Extension Tool
By
–
-
LLM Development Methods: Prompting, Fine-tuning, Few-shot
By
–
In addition to prompting LLMs, many developers are now also experimenting with fine-tuning. I describe in The Batch how to choose from the growing menu of options for building applications with LLMs: Prompting, few-shot, fine-tuning, pre-training.
-
Semantic Search with LLMs Course Launch
By
–
We are thrilled to launch the “Semantic Search with LLMs” course in partnership with @DeepLearningAI_ and @AndrewYNg. In this 1 hour hands-on course taught by Jay and Luis, you’ll learn how to combine the power of LLMs and search to build applications using concepts like… https://t.co/mSC3hkLPfa
— Cohere (@cohere) 16 août 2023We are thrilled to launch the “Semantic Search with LLMs” course in partnership with @DeepLearningAI_ and @AndrewYNg
. In this 1 hour hands-on course taught by Jay and Luis, you’ll learn how to combine the power of LLMs and search to build applications using concepts like -
LLM Fallbacks: Chain-Level Prompt Switching Strategy
By
–
Fallbacks Importantly, not just at the LLM level, but at the chain level Why does this matter? Different LLMs need different prompts. If you hit a rate-limit error on OAI and want to switch to Anthropic, you don't just want to retry with the same prompt – you want to switch
-
System Message Optimization for AI Function Agents
By
–
i would probably tell it explicitly in the system message what you just wrote – "if you do not find a person in the prof, search in founder" or someting also would use OPENAI_FUNCTIONS agent
-
Meta AI Introduces Shepherd: A Model for Critiquing and Refining Responses
By
–
New research from Meta AI — Shepherd is a language model specifically tuned to critique model responses & suggest refinements. It goes beyond the capabilities of untuned models to identify diverse errors & suggest improvements. Read the paper https://
bit.ly/3QC4AW3 -
Improving AI Agents for CSV Question-Answering Applications
By
–
This started ~2 weeks ago, when I tweeted that we wanted to improve our chains/agents for doing question/answering over CSV data Why? Most QA applications focus on text data, but lots of real world data is in CSVs
-
Comparing LLMs: Llama2 vs OpenAI A/B Testing Workshop
By
–
There are a lot of options when it comes to choosing an #LLM. So how do you choose which option is right for you? Check out this virtual workshop "#Llama2 or OpenAI? How to compare LLMs using A/B testings" with @Predibase Data Scientist, @DalianaLiu
. -
Llama 2 Demonstrates Surprising Tool Use Emergence
By
–
Tell Llama 2 about the tools it can use. It has surprising “tool use emergence.”
-
Temperature Settings for Creative vs Factual Llama Output
By
–
Play with the temperature. “A hot Llama never says the same thing twice.” Use higher temp for creative output, low for fact retrieval. Don't go too hot: