One initial countermeasure we add to our AI agents at Coordinal is something like, “If a research result is surprising, assume that there is a bug and rigorously debug the code until you find it.” It’s obviously not enough to just add this as a system prompt, but it’s an important lesson that you find out even as a human researcher (that may have fooled you much more when starting out).
One initial countermeasure we add to our AI agents at Coordinal is something like, “If a research result is surprising, assume that there is a bug and rigorously debug the code until you find it.” It’s obviously not enough to just add this as a system prompt, but it’s an important lesson that you find out even as a human researcher (that may have fooled you much more when starting out).