AI (LLMs), Agents, MCP, Open Claw, Coding Assistants

null

...
Joined
Nov 12, 2014
Messages
34,680
Reputation
6,793
Daps
53,247
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
203,127
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
 

null

...
Joined
Nov 12, 2014
Messages
34,680
Reputation
6,793
Daps
53,247
Reppin
UK, DE, GY, DMV
I've been looking at open claw: OpenClaw — Personal AI Assistant .

It's wild. I reinstalled a small GMKtec mini PC (linux) and will try to set up Open Claw (OC) on that.

From what I have read MPC doesn't use MPC.

You interact with OC via a configured chat "Channel" on a messaging service, such as WhatApp.

OC figures out what to do using a configured LLM (such as ChatGPT) through use of formal output prompts.

OC performs the actions indicated by the LLM using configured "Skills".



You give OC full rights to perform actions on the host it is installed on.

OC inventor Peter Steinberger has been hired by Open AI.

 
Top