Az OpenAI mérnökei részletesen ismertették a ChatGPT hirdetési architektúráját, amely gyökeresen eltér a hagyományos keresőmotorok reklámrendszereitől. A ChatGPT nem egyes keresési kifejezésekre reagál, hanem egy állapottartó munkafolyamatban követi a több lépésből álló beszélgetések kontextusát és a felhasználó változó céljait.
A hirdetési folyamatot egy külön erre a célra finomhangolt ágens alapú nyelvi modell irányítja, amely eszközhívásokkal végzi a releváns hirdetések keresését, rangsorolását és az aukciók lebonyolítását. Ez az ágens képes megkülönböztetni a korábbi kontextust a felhasználó aktuális szándékától, így elkerüli, hogy minden említett termékre azonnal reklámot jelenítsen meg.
A rendszer legfontosabb szerkezeti eleme a teljes elkülönítés: a hirdetési motor független infrastruktúrán és külön modellen fut. Ez garancia arra, hogy a reklámok nem torzítják a ChatGPT válaszait, és ha nem található megfelelő minőségű hirdetés, a rendszer egyszerűen nem jelenít meg semmit. A megoldás sikeresnek bizonyult, a ChatGPT Ads üzletág éves bevétele az indulást követő 200 napon belül elérte az 1 milliárd dollárt.
Az eredeti szöveg (OpenAI)
By Ritendra Datta and Karthik Gopalratnam, Members of Technical Staff
Traditional advertising systems are built to respond to discrete units of user intent. A user searches for or views something online, the ads system receives those queries and page views as events, and the system looks for matching ads based on those events. Building an ads stack for ChatGPT was different: user intent develops across conversations and shifts over multiple turns of a conversation, sometimes without a fitting advertising moment. To support this new paradigm, we built a bespoke ads delivery system. This new type of ad stack is based on a custom, post-trained frontier LLM that makes tool calls for retrieval (identifying the top options), ranking (predicting user engagement), relevance (evaluating the usefulness of the ad), and running auctions for final ad selection and pricing.
Our ads system supports the nuance of evolving user goals by making three key design decisions: 1) implementing stateful ads sessions, meaning information is remembered across turns of a conversation and across multiple conversations, 2) relying on a custom, post-trained LLM that uses a tool call architecture to interpret a conversation’s context and underlying intent, and then effectively select, rank, and deliver ads, and 3) running the ads selection process separately from ChatGPT’s answer generation, in its own service, to keep ads from influencing answers and maintain ChatGPT’s neutral voice. We use our post-trained LLM to orchestrate the entire ads flow, determining the right ad to surface at the right time based on both the user’s current turn and conversation history. While bootstrapping a self-improving ads system like this used to take years, ChatGPT Ads reached $1 billion in annualized revenue run rate less than 200 days after launch; now, more than 100,000 advertisers have run ads on ChatGPT since launch.
A conventional advertising request usually starts with a well-defined event. A user submits a search query or opens a webpage and the ads system receives a request. This type of system is fairly simple: it retrieves potential ad candidates, ranks them, runs an auction to appropriately price the opportunity, and shows the resulting ad to the user. ChatGPT does not naturally produce such a concrete moment.
In a ChatGPT conversation, people arrive with goals rather than a one-answer search query. They might be planning a trip, choosing software for their business, furnishing a home, or learning a new hobby. This doesn’t all happen in one turn of a conversation. ChatGPT often helps the user clarify what matters along the way.
As an example, our engineering team asked ChatGPT how to train for a race: A conversation begins with a general question about running. Several turns later, they ask about shoes to help train. The commercial meaning of the conversation changes as each constraint arrives—and this personalized context evolves across multiple sessions. A system that acted on the first message could retrieve the wrong intent entirely, potentially degrading the user’s experience and getting in their way.
Building our ads system required us to move beyond the request-response advertising architecture and build an ads stack from scratch to find potential economic opportunities while prioritizing user trust or value.
Turning every message into a standalone request, like a traditional ads system, would have carried a few risks in our chat use case: 1) misreading the user goal by oversimplifying it, 2) beginning the advertising flow too soon, before the user’s real need has become clear, 3) showing ads that get in the way of the user journey instead of supporting it, and 4) inefficiently rerunning the ads flow every time the request changes, creating noise and wasting cost. Instead of building around individual events, the ads system (consisting of retrieval, ranking, and delivery) maintains a stateful session, meaning the ads session runs for the duration of
