Comment by hpdigidrifter
2 days ago
Can't speak for copilot but Gemini cli is unbelievably bad compared to Gemini web.
CC has some magic secret sauce and I'm not sure what it is.
My company pays for both too, I keep coming back to Claude all-round
2 days ago
Can't speak for copilot but Gemini cli is unbelievably bad compared to Gemini web.
CC has some magic secret sauce and I'm not sure what it is.
My company pays for both too, I keep coming back to Claude all-round
Claude Code is one of a very few AI tools where I genuinely think the people at the company who build it use it all the time.
They absolutely do, the CEO has come out and said a few engineers have told him that they dont even write code by hand anymore. To some people that sounds horrifying, but a good engineer would not just take code blindly, they would read it and refine it using Claude, while still saving hundreds of man hours.
> They absolutely do, the CEO has come out and said a few engineers have told him that they dont even write code by hand anymore. To some people that sounds horrifying, but a good engineer would not just take code blindly, they would read it and refine it using Claude, while still saving hundreds of man hours.
TBH, that isn't sustainable. Skills atrophy. At some point they are going take the code blindly.
Considering what they have said in the past about agentic code changes, they are already doing just that - blindly approving code from the agent. I say this because when I last read what one of their engineers on CC tweeted/posted/whatever, I thought to myself "No human can review that many lines of code per month"[1].
---------
[1] IIRC, it was something stupid like 30kLoc reviewed in a month by a single engineer.
1 reply →
He does !
https://x.com/bcherny/status/2007179832300581177
I know they do because of how painfully awful the Claude web/Claude desktops uxui is, as well as performance.
watch the interviews with Boris. He absolutely uses it to build CC.
s/AI//
I would love to hear/see a definitive answer for this, but I read somewhere that the relationship between MS and \A is such that the copilot version of the \A models has a smaller context window than through CC.
This would explain the "secret sauce", if it's true. But perhaps it's not and a lot is LLM nondeterminism mixing with human confirmation bias.