PR ☮ ♥ ♬ 🧑‍💻 · @peterrenshaw
352 followers · 1524 posts · Server ioc.exchange

remember the rogue AI drone mentioned at the “Future Combat Air and Space Capabilities Summit in London, May 2023”?

“A US air force colonel “misspoke” when he said at a Royal Aeronautical Society conference last month that a drone killed its operator in a simulated test because the pilot was attempting to override its mission, according to the society.”

Nothing to see here, move along.

/ / / / / / <theguardian.com/us-news/2023/j>

#ai #LLM #alignmentproblem #counterintel #RAS #drones #usaf

Last updated 1 year ago

Gabor Hrasko · @ghrasko
10 followers · 41 posts · Server newsie.social

SCAR TISSUE

Tobias S. Buckell's novel is practically about the ...

“You need to be raised, and in your own body. You’re not just a mind in a jar—that’s an old theory of consciousness. You’re a grown being. A whole being. Your gut bacteria, spinal column, the society around you, all of that creates an entire person, as well as the experiences and time that it passes through. You can’t just manufacture a thinking robot. We have to raise it.”

slate.com/technology/2020/05/s

#scifi #ai #alignmentproblem

Last updated 1 year ago

Freedom Baird · @freedom_baird
112 followers · 513 posts · Server mas.to

Interesting and informative interview with OpenAI co-founder and chief scientist Ilya Sutskever

Good clarity and context around OpenAIs approach to LLMs

I noted a few key points in the reply below

(I have personal interest in this but also will present on it as work next month)

youtube.com/watch?v=UHSkjro-Vb

#alignmentproblem #neuralnetwork #bingchat #chatgpt #ilyasutskever #openai #llm

Last updated 2 years ago