Chaos Engineering The behavior of LLMs can be unpredictable and chaotic ChatChaos is a fake LLM by @andrewnguonly specifically designed to return invalid JSON, hallucinate, and have long response times Can be used to stress test your system! Blog:
PROMPT ENGINEERING
-
Understanding Log Probabilities Parameter in Language Models
By
–
Hey Amy, following up on this, the top logprobs number is just setting how many log probs you want returned, not the range. The range can be any negative number to 0 but that is different than the top logprobs parameter.
-
ChatGPT for Content Rewriting and Introductory Language Suggestions
By
–
Marzyeh Ghassemi uses ChatGPT for rewriting content in different styles, like making scientific abstracts more suitable for a general audience. She also uses it to suggest introductory language for articles, emails, or papers.
-
ChatGPT in Education: Teaching with AI Tools and Critical Thinking
By
–
Siddharth Kankaria uses ChatGPT to brainstorm prompts, questions, and content for classroom activities. He also encourages students to use AI tools while being aware of their limitations.
-
Official OpenAI Guide to Prompt Engineering
By
–
OpenAI released their official Prompt Guide, offering six key strategies: Providing clear instructions
Supplying reference text
Breaking down complex tasks
Allowing models time to 'think,' utilizing external tools
Conducting targeted evaluations https://platform.openai.com/docs/guides/prompt-engineering?utm_source=aibreakfast.beehiiv.com&utm_medium=referral&utm_campaign=openai-releases-official-prompt-guide-for-free
… -
AI Breakfast for Monday, December 18th
By
–
AI Breakfast for Monday, December 18th Running Mixtral 8x7b, OpenAI's official Prompting Guide, and how Google is being sued for essentially killing their own business model with AI:
-
Cohere RAG Chatbot with Quickstart Connectors Guide
By
–
Cohere Chat with RAG comes with quickstart connectors – around 100 pre-built connector implementations, including Slack, Elastic, GitHub, Google Drive, and more. In this LLM University chapter, learn about RAG with quickstart connectors. https://
txt.cohere.com/rag-chatbot-qu
ickstart/
… -
GPT Model Hallucinations and Token-Level Confusion Explained
By
–
It’s a hallucination, likely because at the token level, gpt-3.5-turbo and gpt-4.5-turbo would be represented similarly and the model already knows it has gpt-4 access in some cases. Plus we called the new model gpt-4 turbo which has added to the confusion.
-
RPG Game with GPT Agents as DM-Controlled Characters
By
–
A RPG game (think paper/pen, d&d, dsa, etc) where you play the DM and GPT agents play the characters. There is a baseline story, you adjust the situations as needed. The characters actively try to outsmart the story while staying in character. One of the agents could be a human
-
OpenAI releases official prompt engineering guide
By
–
Here’s the official prompt engineering guide from @OpenAI
, created by @joepalerm0 and @sandersted https://
platform.openai.com/docs/guides/pr
ompt-engineering
…