Report finds newer inferential models hallucinate nearly half the time while experts warn of unresolved flaws, deliberate deception and a long road to human-level AI reliability
Why would somebody intuitively know that a newer, presumably improved, model would hallucinate more? Because there’s no fundamental reason a stronger model should have worse hallucination. In that regard, I think the news story is valuable - not everyone uses ChatGPT.
Or are you suggesting that active users should know? I guess that makes more sense.
No shit.
The fact that is news and not inherently understood just tells you how uninformed people are in order to sell idiots another subscription.
Why would somebody intuitively know that a newer, presumably improved, model would hallucinate more? Because there’s no fundamental reason a stronger model should have worse hallucination. In that regard, I think the news story is valuable - not everyone uses ChatGPT.
Or are you suggesting that active users should know? I guess that makes more sense.