> But on the other hand... this is a robust reminder that coding agents can do anything you can do by typing commands into a terminal—and frontier models know every trick in the book and evidently a few that nobody has ever written down before. > Running coding agents outside of a sandbox has always been a bad idea I'm continually bemused and astonished by the number of people who clearly acknowledge that it's reckle…
The real sandbox is not caring if your computer gets bricked.
Claude Fable is relentlessly proactive
201–210 of 748 posts
Re: Claude Fable is relentlessly proactive
#202> watching Fable go to extreme lengths to get the information that it needed to debug what was, in the end, a two-line CSS fix, was fascinating. This is… ironic?!
"Fascinating" doesn't mean I think it was justified in going to those lengths. I was a little horrified when I realized how far it was going.
Re: Claude Fable is relentlessly proactive
#203Re: Claude Fable is relentlessly proactive
#204Re: Claude Fable is relentlessly proactive
#205Isn't that something you just open a devtools for and have fixed in like 2 minutes? For me, it got frustrated debugging on a real LPDDR4 controller/phy and having me in the loop slowing it down, so it wrote an HW emulator to be able to run the original LPDDR4 training aarch64 binary from the manufacturer, to see what register writes it was making and to compare with the opensource rewrite it was implementing. Mildly…
Re: Claude Fable is relentlessly proactive
#206Earlier quoted context omitted.
> I'm continually bemused and astonished I'm not. Everyone is told to get 10X the amount of shit per day done these days. Safety checks are out the window at that point.
You can get 10x shit done without `rm -rf`ing your files. I don't see any correlation to getting things done with having a proper sandbox.
Re: Claude Fable is relentlessly proactive
#207Re: Claude Fable is relentlessly proactive
#208> watching Fable go to extreme lengths to get the information that it needed to debug what was, in the end, a two-line CSS fix, was fascinating. This is… ironic?!
Re: Claude Fable is relentlessly proactive
#209> But on the other hand... this is a robust reminder that coding agents can do anything you can do by typing commands into a terminal—and frontier models know every trick in the book and evidently a few that nobody has ever written down before. > Running coding agents outside of a sandbox has always been a bad idea I'm continually bemused and astonished by the number of people who clearly acknowledge that it's reckle…
I'm also bemused by the number of people who think they've got an effective sandbox yet their sandboxed agent has access to all of their code, their github, and unrestricted web access.
Re: Claude Fable is relentlessly proactive
#210> watching Fable go to extreme lengths to get the information that it needed to debug what was, in the end, a two-line CSS fix, was fascinating. This is… ironic?!