Hacker News Reader

Comment by iLoveOncall | Hacker News Reader

LLM labs dumbed down the definition of AGI as much as possible, yet their models haven't reached it still. We are nowhere near the original definition of AGI. Not even 1% of the way there.

View on HN

Oh yeah? Who even talks about the Turing Test anymore? Half a decade ago,that was the informal benchmark.

Not at all.

The Turing test was never about AGI, just about being able to discern a chatbot from a human in a casual conversation...

I would also say that funnily enough it's extremely easy to detect if you're talking to a human or an LLM after a few messages.

We wouldn't be having any talk about AI Slop if it was impossible to tell AI apart from people.

Uhuh, but if it was so easy, we also wouldn't be funding billions of euros and dollars in anti-AI-disinformation systems, holding entire conferences about deepfakes and hybrid attacks on civilians, and have dozens of governments opening entirely new defense departments to study and counter the capabilities of AI to disseminate human-like disinformation at scale (which has been affecting elections across the world).

But yeah, your AI slop take about the local burger joint that used free chatgpt to generate a menu filled with typos and bad images is A+.

in 2023 i wouldve said gpt could pass the turing test. today i could figure out it was an llm in a few turns no problem. llms cannot pass the turing test now that we’re accustomed to them

The only reason you can figure it out is because of the system prompt which is designed to make model “useful”, safe and compliant.

Raw modern LLM with different pre-prompt will easily fool anyone.

Reply on news.ycombinator.com