I haven’t encountered this bug, but I have been frustrated that there’s no way to give a babysitter temporary access to the cameras in the kids’ rooms.
I ended up hosting a local site that embeds the RTSP feeds, which works pretty well, but I was surprised that there’s no native way to do it
It’s funny that this is probably due to bias in the training texts, right? Humans are way more likely to publish their “Eureka!” moments than their screwups… if they did, maybe models would’ve exhibit this behavior.
Now that AI labs have all these “Nevermind” texts to train on, maybe it’s getting easier to correct? (Would require some postprocessing to classify the AI outputs as successful or not before training)
"At some point I realized that rather than do something else until it finishes, I would constantly check on it to see if it was asking for yet another permission, which felt like it was missing the point of having an agent do stuff"
Why don't Claude Code & other AI agents offer an option to make a sound or trigger a system notification whenever they prompt for approval? I've looked into setting this up, and it seems like I'd have to wire up a script that scrapes terminal output for an approval request. Codex has had a feature request open for a while: https://github.com/openai/codex/issues/3052
> wants it moved over to the others side of the utility closet so that when you open the door it is easier to put clothes from there into the dryer
That's when you swap the hinges so the door opens the other way, and you thank the manufacturer for providing such an easy solution to a common problem. It's good to keep things flexible and user-configurable.
Now quick, someone reply with a counterexample of how user configuration complicates the product and increases cost. It's design tradeoffs all the way down...
I ended up hosting a local site that embeds the RTSP feeds, which works pretty well, but I was surprised that there’s no native way to do it