minus-squaregr3q@lemmy.mltoTechnology@lemmy.world•Reasoning failures highlighted by Apple research on LLMslinkfedilinkEnglisharrow-up5·edit-223 days agoI tested chatgpt, it needed some nagging but it could do it. Needed the size, blank and white keywords. Obviously a lot harder than it should be, but not impossible. linkfedilink
I tested chatgpt, it needed some nagging but it could do it. Needed the size, blank and white keywords.
Obviously a lot harder than it should be, but not impossible.