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
[ Parent
| on HN ]
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?
Not on calculations that involve counting at a sub-token level. Otherwise, it depends.
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.
Coding is not one of those cases or edge cases wouldn't exists
“Already 5xs”
Even AI marketing doesn’t claim this. Totally baseless claim given how many people report negative experiences trying to use AI.