Harrison Chase@hwchase17

1 year ago

I think a lot of people are sleeping on using claude-sonnet to do meta-prompting/prompt optimization we found its better than o1 (and cheaper/faster) it still struggles for complex tasks (curious to see how o3 would do) but it works quite well for simpler one https://t.co/AymCk48MkF

samim@samim

1 year ago

After testing Deepseek R1 and OpenAI O1 extensively, i still find Claude 3.5 Sonnet with this system prompt far more useful for most tasks i do daily: https://t.co/PhneoO2LWw

LangChain@LangChainAI

1 year ago

📀Exploring prompt optimization We created 5 different datasets and 5 different algorithms for prompt optimization. Here's what we learned: 🥇Claude sonnet performs best (> o1) 🧠Prompt optimization ~ memory: most effective on tasks where the model lacks domain knowledge https://t.co/8pno8efJoB