News for hackers. Stuff that matters.
Re:Claude 3.7 Sonnet and Claude Code by OsrsNeedsf2P on Monday February 24, 2025 @03:20PM (#43164464)
This test has always been so stupid since models work at the token level. Claude 3.5 already 5xs your frontend dev speed but people still say "hurr durr it can't count strawberry" as if that's a useful problem
Re:Claude 3.7 Sonnet and Claude Code by dannyw on Monday February 24, 2025 @03:32PM (#43164613)
The problem also comes to LLMs being confidently wrong when it’s wrong.
Re:Claude 3.7 Sonnet and Claude Code by bufferoverflow on Monday February 24, 2025 @04:47PM (#43165334)
This test isn't stupid. If it can't count the number of letters in a text, can you rely on it with more important calculations?
Re:Claude 3.7 Sonnet and Claude Code by TeMPOraL on Monday February 24, 2025 @08:03PM (#43166849)
Not on calculations that involve counting at a sub-token level. Otherwise, it depends.
Re:Claude 3.7 Sonnet and Claude Code by stnmtn on Monday February 24, 2025 @05:23PM (#43165641)
You can rely on it for anything that you can validate quickly. And it turns out, there are a lot of problems which are trivial to validate the solution to, but difficult to build the solution.
Re:Claude 3.7 Sonnet and Claude Code by 101008 on Monday February 24, 2025 @06:00PM (#43165963)
Coding is not one of those cases or edge cases wouldn't exists
Re:Claude 3.7 Sonnet and Claude Code by elicksaur on Monday February 24, 2025 @09:28PM (#43167381)
“Already 5xs”

Even AI marketing doesn’t claim this. Totally baseless claim given how many people report negative experiences trying to use AI.

Re:Claude 3.7 Sonnet and Claude Code by ssijak on Tuesday February 25, 2025 @03:51AM (#43169619)
Some people report some negative experiences for any tool ever brought into existence.