We're heading to @NeurIPSConf in Vancouver! Attend our #Dev Demos Discover our latest research papers on #AI & #ML Explore our Prompt Challenges If you're attending, stop by booth 56 & say hi! #NeurIPS
PROMPT ENGINEERING
-
Automating Emails with ChatGPT and AI Bolt
By
–
I automated my emails with #ChatGPT o1 and #AI Bolt—it's AMAZING! Here’s how it works and how you can do the same → https://youtu.be/vE9adtV6MZw This is my BEST video EVER—drop your likes and shares to help me in the algorithm!
-
Reasoning Models Perform Better With Simple Prompts
By
–
As OpenAI writes in their documentation (https://platform.openai.com/docs/guides/reasoning#advice-on-prompting), these models perform best with simple prompts. "Advanced" techniques, like few-shot prompting or instructing the model to "think step by step," may not enhance performance and can sometimes hinder it.
-
Internal Reasoning Makes Step-by-Step Prompts Unnecessary
By
–
• Avoid chain-of-thought prompts: Since this model performs reasoning internally, prompting them to "think step by step" or "explain your reasoning" is unnecessary.
-
Keep AI Prompts Simple and Direct for Better Results
By
–
• Keep prompts simple and direct: This model better understands and responds to brief, straightforward instructions without extensive guidance.
-
LLM comparison: which models solved the contrived problem?
By
–
Contrived problem, I know, but: ChatGPT 4o, o1-mini, and Claude 3.5 Sonnet all get this wrong — 0 out of 3 each ChatGPT o1 gets it right 3 out of 3
-
Developing a new prompt library
By
–
Working hard on my new prompt library 😉
— God of Prompt (@godofprompt) 5 décembre 2024
COMING SOON 🥳 pic.twitter.com/ncgFxaO3FEWorking hard on my new prompt library 😉 COMING SOON
-
Abacus ChatLLM Teams: Multi-Modal AI Agent Platform with Multiple LLMs
By
–
Get @AbacusAI ChatLLM Teams: https://t.co/73VwIlbKFB <=> able to summarize, to build #AI agents from, or to chat with multi-modal data sources (PDF, text, images…), using any #LLMs :: Llama-3 on Grok, Claude Opus, Gemini, GPTs, or Abacus Smaug (an incredible open-source model). pic.twitter.com/F8drm4R6kb
— Kirk Borne (@KirkDBorne) 5 décembre 2024Get @AbacusAI ChatLLM Teams: https://
chatllm.abacus.ai/?token=kirk able to summarize, to build #AI agents from, or to chat with multi-modal data sources (PDF, text, images…), using any #LLMs :: Llama-3 on Grok, Claude Opus, Gemini, GPTs, or Abacus Smaug (an incredible open-source model). -
O1 Pro Demonstration with 6 Criteria Challenge
By
–
O1 pro mode demo to showcase a complex prompt handling. 6 criteria challenge
-
Uploading AI Crew to Claude Sonnet for Optimization
By
–
Good job Would it be possible to upload this entire crew (in some structured form) to Sonnet and let it ask to improve it or adapt for new use case?