Coding is the PS5's RTMP stream

"Most software that requires hiring and paying software engineers has low risk tolerance" The problem is that this statement simply isn't true. Most software engineers do not work on low risk tolerance code. Am I getting out of touch with the level of output current models can do, and I mean hard problems too.

It's funny because, I think the blocker might be how efficient the context is compacted and sending around between these agents. Claude Code does most of this stuff now already, in terms of maintainability, money, time to change it, and so on. The author is right to categorise AI as a rubber ducky, I think this is good AI use! “Most software that requires hiring and paying software engineers has low risk tolerance" The problem is that this statement simply isn't true. Most software engineers do not work on low risk tolerance code.

What a nice article. If I ever get in a situation where my manager demands I have to write 0.86 instead of .86. The future is now. There are exceptions like antirez, but I think this is awesome! I'm going to be selling Muse into your company as your AI coworker.