kcarruthers , 23 days ago

I have been waiting for this story to drop: @mpesce stumbled upon LLM Kryptonite – and no one wants to fix this model-breaking bug

Models with flaws can be harmless … yet dangerous. So why are reports of problems being roundly ignored?

https://www.theregister.com/2024/05/23/ai_untested_unstable/