Getting an agent working via an existing Slack setup is fairly effortless and the control over output format is useful
I had a look at getting same agent up in WhatsApp but it seems to need FB business acc to even start process, to get FB business you need an FB personal etc. ... looked like too much effort
You can still look at almost any codebase and ask 'why is this bit not using a state machine here?' ... the AASM repo readme is very accessible even if you don't know Ruby: https://github.com/aasm/aasm
The counternarrative is that it is a very accomplished piece of work that most in the sector were not expecting -- it's open source with API available at fraction of comparable service cost
It has upended a lot of theory around how much compute is likely needed over next couple of years, how much profit potential the AI model vendors have in nearterm and how big an impact export controls are having on China
V3 took top slot on HF trending models for first part of Jan ... r1 has 4 of the top 5 slots tonight
Almost every commentator is talking about nothing else
(I had same issue, just asked it to check some code that 4.8 had modified earlier in day)