One of the takehome lessons from ChaosGPT and AutoGPT is that there’ll likely end up being agential AIs, even if the original AI wasn’t particularly agentic.
AutoGPT is an excellent demonstration of the point. Ask someone on this forum 5 years ago whether they think AGI might be a series of next token predictors strung together with modular cognition occurring in English and they would have called you insane.
Yet if that is how we get something close to AGI it seems like a best case scenario since intrepretability is solved by default and you can measure alignment progress very easily.
One of the takehome lessons from ChaosGPT and AutoGPT is that there’ll likely end up being agential AIs, even if the original AI wasn’t particularly agentic.
AutoGPT is an excellent demonstration of the point. Ask someone on this forum 5 years ago whether they think AGI might be a series of next token predictors strung together with modular cognition occurring in English and they would have called you insane.
Yet if that is how we get something close to AGI it seems like a best case scenario since intrepretability is solved by default and you can measure alignment progress very easily.
Reality is weird in very unexpected ways.