Re:GPT-5.5
by camgunz on Friday April 24, 2026 @02:55AM
(#47886585)
Hallucination benchmarks accept "I don't know", which Haiku did at least a little. Here are other benchmarks corroborating: https://suprmind.ai/hub/ai-hallucination-rates-and-benchmark...
[ Parent
| on HN ]
There are no comments on this comment yet.