Boris Cherny

@bcherny

Also note that well aligned models are not sufficient to solve prompt injection by themselves yet. That said, we have solved prompt injection in practice when layering our latest models with prompt injection probes (on by default for all traffic) and auto mode (also on by default). The little bit of scaffolding helps. https://x.com/bcherny/status/2085860677990883454?s=46
打开原帖#511482
  1. Research

    Rohan Paul: The paper shows that refreshing an agent's memory does not refresh its plan, so the plan should be checked again before execution.
  2. Research

    Rohan Paul: https://www.reuters.com/world/asia-pacific/openai-says-working-with-samsung-next-generation-chips-deepening-cooperation-2026-09-09/
  3. Research

    Rohan Paul: OpenAI is jointly researching and producing new AI chips with Samsung Electronics, its Korea office said