[chrsw]

I’m not an AI researcher but I’m not convinced these contemporary artificial neural networks will get us to AGI, even assuming an acceleration to current scaling pace. Maybe my definition of AGI is off but I’m thinking what that means is a machine that can think, learn and behave in the world in ways very close to human. I think we need a fundamentally different paradigm for that. Not something that is just trained and deployed like current models, but something that is constantly observing, constantly learning and constantly interacting with the real world like we do. AHI, not AGI. True AGI may not exist because there are always compromises of some kind.

But, we don’t need AGI/AHI to transform large parts of our civilization. And I’m not seeing this happen either.

[BosunoB]

You are absolutely right that AGI will probably barely resemble LLMs, but this is kind of beside the point. An LLM just has to get good enough to automate sufficiently complicated coding tasks, like those of coding new AI experiments. From there, researchers can spin off new experiments rapidly and make further improvements. An AGI will likely have vastly different architecture from an LLM, but we will only discover that through likely hundreds of thousands of experiments with incremental improvements.

This is the ai-2027.com argument. LLMs only really have to get good enough at coding (and then researching), and it's singularity time.

[chpatrick]

I feel like every time AI gets better we shift the goalposts of AGI to something else.

[chrsw]

I don't think we shift the goalposts for AGI. I'm not getting the sense that people are redefining what AGI is when a new model is released. I'm getting the sense that some people are thinking like me when a new model is released: we got a better transformer, and a more useful model trained on more or better data, but we didn't get closer to AGI. And people are saying this not because they've pushed out what AGI really means, they're saying this because the models still have the same basic use cases, the same flaws and the same limitations. They're just better at what they already do. Also, the better these models get at what they already do, the more starkly they contrast with human capabilities, for better or worse.