immediate on GPT-o1

OpenAI’s newest mannequin household, GPT-o1, guarantees to be extra highly effective and higher at reasoning than earlier fashions. 

Utilizing GPT-o1 can be barely totally different than prompting GPT-4 and even GPT-4o. Since this mannequin has extra reasoning capabilities, some common immediate engineering strategies gained’t work as effectively. Earlier fashions wanted extra steering, and folks took benefit of longer context home windows to supply the fashions with extra directions.

In response to OpenAI’s API documentation, the o1 fashions “carry out finest with easy prompts.” Nonetheless, strategies like instructing the mannequin and shot prompting “could not improve efficiency and might generally hinder it.” 

OpenAI suggested customers of o1 to consider 4 issues when prompting the brand new fashions:

• Maintain prompts easy and direct and don’t information the mannequin an excessive amount of as a result of it understands directions effectively
• Keep away from chain of thought prompts since o1 fashions already causes internally
• Use delimiters like triple citation markets, XML tags and part titles so the mannequin can get readability on which sections it’s deciphering
• Restrict further context for retrieval augmented era (RAG) as a result of OpenAI mentioned including extra context or paperwork when utilizing the fashions for RAG duties might overcomplicate its response

OpenAI’s recommendation for o1 vastly differs from the strategies it gave to customers of its earlier fashions. Beforehand, the corporate urged being extremely particular, together with particulars and giving fashions step-by-step directions, GPTo1 will do higher “considering” by itself about the way to resolve queries. 

Ethan Mollick, a professor on the Wharton College of Enterprise on the College of Pennsylvania, mentioned in his One Helpful Factor weblog that his expertise as an early consumer of o1 confirmed it really works higher on duties that require planning, the place the mannequin concludes the way to resolve issues by itself. 

Immediate engineering and making it simpler to information fashions 

Immediate engineering, in fact, grew to become a technique for folks to drill down on specifics and get the responses they need from an AI mannequin. It’s grow to be not simply an necessary talent but additionally a rising job class. 

Different AI builders launched instruments to make it simpler to craft prompts when designing AI functions. Google launched Immediate Poet, constructed with the assistance of Character.ai, which integrates exterior information sources to make responses extra related. 

GPT-o1 remains to be new, and persons are nonetheless determining precisely the way to use it (together with me, who has but to determine my first immediate). Nonetheless, some social media customers predict that folks must change how they strategy prompting ChatGPT.