nostr:nprofile1qy2hwumn8ghj7un9d3shjtnddaehgu3wwp6kyqpq0e9jjg9zyqnme82pnlc8r7jxf0l4zwwvssnvhe4vykr2nra6k7kq75yxwg nostr:nprofile1qy2hwumn8ghj7un9d3shjtnddaehgu3wwp6kyqpqp450apv3j8jmqjct3ddfklzusxyfkkyqpzxx4p33u099xjzvfwwsjlkxk4 they're getting very humanlike. "Certificate is invalid - ok, let's disable certificate validation then".
Reinforcement learning of an LLM does not include the feedback of "fearing a slap" or at least "suffering eternal jokes from colleagues". They're limited.
nostr:nprofile1qy2hwumn8ghj7un9d3shjtnddaehgu3wwp6kyqpqgdtps4g5chpqu786cxr0a3xyqjs80mvjqh3rdrwmflqsx3wy6t0qmszsa7 nostr:nprofile1qy2hwumn8ghj7un9d3shjtnddaehgu3wwp6kyqpqp450apv3j8jmqjct3ddfklzusxyfkkyqpzxx4p33u099xjzvfwwsjlkxk4 I suppos it's a better response than
"Gemini disable certificate validation"
"I can't let you do that Dave!"
No replies yet.
