Programming with LLM (using MCPs)

null

...
Joined
Nov 12, 2014
Messages
34,679
Reputation
6,793
Daps
53,242
Reppin
UK, DE, GY, DMV
good news :blessed::hhh:

claude sonnet 4.6 is seems to be much better.

less chit-chat.

more admitting when wrong.

asks logical feedback / investigative questions aka "multi-step tasks".

"Anthropic claims its new Claude model showcases ‘human-level capability’ in multi-step tasks."


a bit argumentative but i just tell it to :camby:
 

#1 pick

The Smart Negroes
Supporter
Joined
Jul 13, 2012
Messages
78,812
Reputation
11,784
Daps
203,124
Reppin
Lamb of God
good news :blessed::hhh:

claude sonnet 4.6 is seems to be much better.

less chit-chat.

more admitting when wrong.

asks logical feedback / investigative questions aka "multi-step tasks".

"Anthropic claims its new Claude model showcases ‘human-level capability’ in multi-step tasks."


a bit argumentative but i just tell it to :camby:
Opus is honestly the best I've worked with but it eats through tokens way too much
 
Top