GPT-4 can barely operate a real web browser (not the summarizing web browser crap that like langchain and auto-gpt provide) without fumbling. I know, because I make it use one. Also, auto-gpt has no guardrails to remove. It just runs prompts in a loop. You're playing with a text predictor. It's useful for NLP and certain tasks, but it's not autonomous. It won't even be able keep a "goal" + the knowledge of the existence of agents it will "copy" + the knowledge of how to use the tools you gave it, because it's limited to 8192 tokens, and 32k at great expense. Even then, there's no proof that the 32k version is any better at using things in its context.

When your supposed super intelligent "AGI" can be completely overwritten by spamming it with nonsense that overwrites its context window, like a dog chases after a squirrel, maybe it's not actually intelligent, and is just predicting text.

I didn't say GPT-4 was superintelligent. This is about further improvements.

When you say future improvements do you mean bigger GPTs? Improved LLM architectures? Different architectures entirely? Are you sure you're not just imagining a thing that would be scary and then saying "what if it was that?".

Can you give an example of a complex technical goal GPT-4 has achieved?

No point, because there are already thousands of such examples on Twitter or wherever on the internet. And since you ask, obviously you intend to find some way to dismiss anything I bring up.

You may have guessed my bias but you are wrong about the intention of my question. I engaged your comment because I thought it was interesting and wanted to know how came to have your opinions.

I realise it's super impressive, it really is. But don't over state what GPT-4 actually is. How on earth would you think an LLM could "copy itself" to anything? What even is "itself" in this context? The weights? Source code or binaries for inference? How about the training parts? You're filling in your gaps of understanding with exciting sci-fi concepts that you half remember, and while that's fun in a 4am dorm-room discussion kind of way it's not useful for thinking about reality.