See the last gemini message in this thread: https://gemini.google.com/share/6d141b742a13

In my opinion still the most egregious example in history of a commercial LLM going off the rails in production. Never any technical postmortem from Google on this.

▲

jackkinsella 2 hours ago | parent | next [-]

It is wild but it was back in 2024 and that's multiple AI lifetimes back.

	▲	bottlepalm an hour ago \| parent [-]
		The problem is newer models are never trained from scratch, they generally just layer on more training data and use the same tools/methods for RLHF. OpenAI, Anthropic, xAI models all have a feel to them that carries over from one generation to the next. Point is, if Gemini is flawed then there's a very good chance that it's still deeply flawed today, and getting smarter at the same time - that is a very bad combination.

▲

wg0 an hour ago | parent | prev | next [-]

Now I really feel worried for the first time.

▲

schmookeeg 2 hours ago | parent | prev | next [-]

wtfffff that gave me sinister chills. Right up the spine. Wow!

▲

kelvinjps10 2 hours ago | parent | prev | next [-]

Wtf I just read

▲

rhaff 2 hours ago | parent | prev [-]

wow