←back to thread

Claude 3.7 Sonnet and Claude Code

(www.anthropic.com)
2127 points bakugo | 4 comments | 24 Feb 25 18:28 UTC | HN request time: 0.001s | source
Show context
meetpateltech ◴[24 Feb 25 19:25 UTC] No.43163764[source]▶
When you ask: 'How many r's are in strawberry?'

Claude 3.7 Sonnet generates a response in a fun and cool way with React code and a preview in Artifacts

check out some examples:

[1]https://claude.ai/share/d565f5a8-136b-41a4-b365-bfb4f4400df5

[2]https://claude.ai/share/a817ac87-c98b-4ab0-8160-feefd7f798e8

replies(3): >>43163937 #>>43164129 #>>43164464 #
OsrsNeedsf2P ◴[24 Feb 25 20:20 UTC] No.43164464[source]▶
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
replies(3): >>43164613 #>>43165334 #>>43167381 #
1. bufferoverflow ◴[24 Feb 25 21:47 UTC] No.43165334[source]▶
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?
replies(2): >>43165641 #>>43166849 #
2. stnmtn ◴[24 Feb 25 22:23 UTC] No.43165641[source]▶
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.
replies(1): >>43165963 #
3. 101008 ◴[24 Feb 25 23:00 UTC] No.43165963[source]▶
Coding is not one of those cases or edge cases wouldn't exists
4. TeMPOraL ◴[25 Feb 25 01:03 UTC] No.43166849[source]▶
Not on calculations that involve counting at a sub-token level. Otherwise, it depends.