Cease Over-Prompting: OpenAI’s New GPT-5.6 Pointers Change Every little thing – Decrypt

In short
OpenAI printed a devoted prompting information for GPT-5.6 Sol that modifications earlier recommendation.
Inner coding-agent checks confirmed lean system prompts improved eval scores by roughly 10–15%.
The information introduces a first-ever part on Programmatic Software Calling and highlights the textual content.verbosity API parameter—each absent from the GPT-5 playbook.
OpenAI printed a brand new prompting information for GPT-5.6 Sol, its newly launched flagship mannequin, and the primary message will really feel unsuitable to anybody who spent the final yr writing multi-page system prompts: cease writing a lot. The core concept is outcome-first prompting. Outline what attractiveness like, set the stopping situations, and get out of the best way.Detailed how-to directions, repeated model guidelines, examples that do not change habits—all of it's now thought-about noise.OpenAI backs this with numbers: In inside coding agent checks, leaner system prompts improved analysis scores by roughly 10–15% whereas slicing complete tokens by 41–66% and prices by 33–67%.GPT-5 vs. GPT-5.6: What really changedThe GPT-5 prompting information, printed at launch in August 2025, was about including scaffolding. You bought XML persistence blocks telling the mannequin to maintain working till the issue was solved, detailed context-gathering templates that mapped precisely easy methods to parallelize searches and when to escalate, and power preamble scripts that narrated each step out loud.The philosophy was calibrating eagerness—constructing specific rails for when to go more durable or stand down.GPT-5.6 largely would not want these rails. The brand new information tells you to trim: repeated guidelines, model directions that do not change habits, examples that do nothing, and course of steps the mannequin already handles reliably. So mainly, that “ block with its parallel search batches and early-stop standards that used to assist is now scaffolding the mannequin has to parse round, not scaffolding that helps it.What you really preserve is easier: the user-visible consequence, success standards, stopping situations, and exhausting constraints. The information's mannequin of immediate begins with “Resolve the shopper's subject finish to finish”—then specifies precisely what achieved appears to be like like, what actions to finish earlier than responding, and what to do when required proof is lacking. Not “be thorough.” Not “preserve going.” Simply: right here is the vacation spot.The danger calculus additionally shifted. The information warns that GPT-5.6 follows immediate contracts carefully, and that “conflicting guidelines can create extra instability than lacking element.”An earlier mannequin would choose one instruction when it hit a battle. GPT-5.6 burns reasoning tokens making an attempt to reconcile each, which is slower, costlier, and sometimes unsuitable. In case your system immediate has overlapping guidelines—and most manufacturing prompts do—that is the factor to repair first.Additionally OpenAI closely advises towards utilizing the outdated trick of resorting to absolutes like “at all times do that” or “by no means do this” to steer the AI’s habits in a selected course.Two concrete additions spherical out the distinction. The primary is the textual content.verbosity parameter: As a result of GPT-5.6 is already extra concise by default than GPT-5.5, outdated “be transient” directions now over-correct and make responses too brief. Set a worldwide default through the parameter, then override per activity within the immediate. The second is a bit on Programmatic Software Calling—for bounded workflows the place code handles filtering, batching, or aggregating massive intermediate outputs and returns a compact consequence, offloading that work from the mannequin's judgment solely.However does it work?We used the information to optimize our immediate for TYPE OR DIE, the first-person typing survival horror recreation we construct to benchmark a mannequin's coding skills. The consequence was extra polished: GPT-5.6 Sol tackled the auto-aim logic extra effectively than on earlier runs, the visuals had extra coherence, and the general really feel of the sport was cleaner.It took extra time to construct. The mannequin did not leap straight to code—it mapped your complete drawback first, deliberate every system earlier than writing a line. That is the information working as meant. Outline the vacation spot; the mannequin chooses the route.The brand new immediate is out there on our Github so you possibly can test it out.You possibly can play the unique GPT 5.6 recreation by clicking on this hyperlink.The sport created below the newer immediate, is out there right here.If you wish to push additional, or are too lazy to memorize all these new tips, you possibly can construct your personal customized GPT and feed it the complete information as its information base. Configure it to research any immediate you throw at it, perceive the underlying logic, and rewrite it in GPT-5.6 model. You find yourself utilizing immediate engineering to engineer higher prompts.Promptception. You are welcome.Every day Debrief NewsletterStart on daily basis with the highest information tales proper now, plus authentic options, a podcast, movies and extra.