I am looking for ideas on what to train a specialized model for!
What is one simple thing you repeatedly ask ChatGPT, Claude, or another model to do that it still somehow messes up?
Ask HN: What is one simple thing LLMs are insanely bad at?
1–10 of 80 posts
Re: Ask HN: What is one simple thing LLMs are insanely bad at?
#2Spatial reasoning and 3d rigging and animation.
Oh, you said simple. Speaking like a human
Re: Ask HN: What is one simple thing LLMs are insanely bad at?
#3being consistent when being asked the same question multiple times
Re: Ask HN: What is one simple thing LLMs are insanely bad at?
#4humor
Re: Ask HN: What is one simple thing LLMs are insanely bad at?
#5These models seem to be bad at writing prose or text. Many of the sentence structures seem to be unvaried.
Re: Ask HN: What is one simple thing LLMs are insanely bad at?
#6Suggesting business names for businesses, I mean they are great, but they already exist, multiple times even.
Re: Ask HN: What is one simple thing LLMs are insanely bad at?
#7being consistent when being asked the same question multiple times
Set temperature to 0
Re: Ask HN: What is one simple thing LLMs are insanely bad at?
#8Short answers to simple questions.
Re: Ask HN: What is one simple thing LLMs are insanely bad at?
#9whenever I ask it for anything load bearing
Re: Ask HN: What is one simple thing LLMs are insanely bad at?
#10They don't generate keyword search queries very well. They can overcome this by brute force but if you watch what they search you will cringe.
nhl toronto scores nhl hockey toronto scores "nhl hockey" toronto score today nhl "hockey score toronto" "hockey" who won toronto
etc.
Somehow being good at semantic search makes them bad at keyword search, for whatever reason.