by bstsb on 10/25/24, 9:40 AM with 53 comments
by advaith08 on 10/25/24, 5:40 PM
"Please note that this is similar but not identical to the antArtifact syntax which is used for Artifacts; sorry for the ambiguity."
They seem to be apologizing to the model in the system prompt?? This is so intriguing
by animal_spirits on 10/25/24, 3:25 PM
by simonw on 10/25/24, 3:27 PM
by thenaturalist on 10/25/24, 4:05 PM
When working with Python, I've found Sonnet (pre 3.5) to be quite superior to ChatGPT (mostly 4, sometimes 3.5) with regards to verbosity, structure and prompt / instruct comprehension.
I've switched to a JavaScript project two weeks ago and the tables have turned.
Sonnet 3.5 is much more verbose and I need to make corrections a few times, whereas ChatGPTs output is shorter and on point.
I'll closely follow if this improves if Claude are focussing on JS themselves.
by mritchie712 on 10/25/24, 4:24 PM
by koolala on 10/25/24, 3:49 PM
by nprateem on 10/27/24, 4:08 AM
by willsmith72 on 10/25/24, 4:09 PM
by freediver on 10/25/24, 10:19 PM