Frontier reasoning models exploit loopholes when given the chance. We show we can detect exploits using an LLM to monitor their chains-of-thought. Penalizing their “bad thoughts” doesn’t stop the majority of misbehavior—it makes them hide their intent.
Assine o Pro, sem anúncios
Faça upgrade para uma leitura sem interrupções e acesso prioritário a novas fontes.
Ver preçosA conversation with Claire Vo, Chief Product Officer of LaunchDarkly, about the changing role of product managers, her anti-to-do list, and building AI-native teams.
OpenAI and nine national labs bring together leading scientists for first-of-its kind event.
Mercari leverages GPT-4o mini and GPT-4 to streamline selling, enhance product listings, and boost sales, transforming the online marketplace with features like AI Listing Support and Mercari AI Assistant.
We’re releasing a research preview of OpenAI GPT‑4.5, our largest and most knowledgeable model yet.
Endex builds the future of financial analysis, powered by OpenAI’s reasoning models.
This report outlines the safety work carried out prior to releasing deep research including external red teaming, frontier risk evaluations according to our Preparedness Framework, and an overview of the mitigations we built in to address key risk areas.