Not Utilizing the Em Sprint

OpenAI has not achieved its objective of creating a superintelligence or synthetic common intelligence, nor has it cracked its deliberate development of an autonomous “AI researcher.” Nevertheless it has discovered how you can get ChatGPT to cease misusing the em sprint. So, that’s one thing.

In a post on X, CEO Sam Altman introduced, “For those who inform ChatGPT to not use em-dashes in your customized directions, it lastly does what it’s purported to do!” He referred to as the event a “small-but-happy win.” The corporate confirmed the potential to chop off the chatbot’s reliance on the punctuation mark in a post on Threads, the place it made ChatGPT write a proper apology for “ruining the em sprint.” Notably, the chatbot was not capable of write the apology with out utilizing an em sprint.

To that time, it looks as if there’s a noteworthy distinction to be made right here. OpenAI has not discovered how you can get ChatGPT to make use of the em sprint in a extra applicable method or to deploy it extra sparingly by default. As an alternative, it has merely given customers the flexibility to inform ChatGPT to not use it, a change that may be made throughout the chatbot’s personalization settings.

That skill follows the release of GPT-5.1, the most recent mannequin from OpenAI. One of many main factors of enchancment that the corporate hammered in its rollout of the brand new mannequin was the truth that GPT-5.1 is outwardly higher at following directions and presents extra personalization options. So the em sprint clampdown seems to simply be one instance of how customers could make use of the mannequin’s extra compliant sensibilities slightly than some repair to the underlying mannequin’s general output.

The truth that the em sprint repair is one thing that has to occur on a user-by-user foundation most likely speaks to simply how a lot of a black field most LLMs are. In reality, there are customers in Altman’s replies on X displaying that, regardless of the instruction, their occasion of ChatGPT continues to spit out em dashes. OpenAI’s presentation of personalization as a resolve would appear to recommend that discovering an answer at scale continues to be actually, actually laborious.

The corporate has seemingly discovered a approach to weight customized directions extra closely inside its calculations when producing a response to a immediate, which might produce a outcome like an individual’s model of ChatGPT not utilizing em dashes. Nevertheless it nonetheless looks as if the corporate can’t work out why the issue occurred within the first place or persists. No marvel the corporate is leaning heavily into personalization and speaking much less about AGI recently.