News for hackers. Stuff that matters.
Re:Grok 4.7 by TomGarden on Monday September 21, 2026 @03:14PM (#49791936)
I think these are the worst I've seen, at least in some time. It's a silly benchmark though, not sure what to make of it
Re:Grok 4.7 by athrowaway3z on Monday September 21, 2026 @04:20PM (#49792826)
I think the result is fine. The benchmark is silly to the point of being useless nowadays.

It used to be a mess in various interesting ways. Now, almost every big release can draw something perfectly functional.

So the question - without a correct answer - given the prompt "Generate an SVG of a pelican riding a bicycle":

Does the user want the least lines of code to make it functional, or the best looking version?

Re:Grok 4.7 by wolttam on Monday September 21, 2026 @06:04PM (#49794067)
The user at the very least expects the bike to have bike geometry; Grok seems to struggle with that
Re:Grok 4.7 by peder on Tuesday September 22, 2026 @07:41AM (#49799693)
exactly, the benchmark just needs to be downvoted into oblivion each times it's posted. The outcome is not deterministic and the model needs to determine what level of detail is appropriate for an svg. There is no wrong answer to this unless it's obviously un-Pelican-like.
Re:Grok 4.7 by Mashimo on Monday September 21, 2026 @04:03PM (#49792606)
If you think this is bad, look up mistral.
Re:Grok 4.7 by paimapi on Monday September 21, 2026 @06:35PM (#49794375)
it's not truly tested until it plays a match or ten in Brood War imo