injections
4 stories and discussions about injections, aggregated from every source we track.
1.
Most developers still treat prompt injection as a leakage problem. Someone types an adversarial...
2.
Research on aligning AI with human values and intent, and reports documenting model failures.
3.
Research on aligning AI with human values and intent, and reports documenting model failures.
4.
In Our framework for reporting model misalignment OpenAI provide "six reports on unexpected or concerning model behavior we’ve observed in the last six months". This one here is my favorite: …