Thanks for posting this. Although I haven't tried the skill yet, it inspired me to put some similar rules in my CLAUDE.md files and I'm very happy with the results. It made interacting with Claude much easier.
Although some of the comments here have complained about the idea, I think they're missing the point. Although the skill and similar rules can be used to hide the fact you're using AI, it can also be used to make interacting with AI easier, i.e. when you're in a long coding session it can be quite daunting to be presented with so many questions and exhausting to look for the important decisions buried in an overwhelming amount of text. For those of us who are using AI to code, which is almost everyone now, this approach is likely to be very useful to reduce the cognitive overload.
In case the author of the post reads these comments… Thank you very much for sharing this with us. My daughter had leukemia (ALL) at a young age - your post gives me a glimpse into how she might have experienced the treatment. She was too young at the time to be able to describe her how it felt.
Probably not anything more complicated than running some kind of signal receiver while clicking each button on the remote and then capturing/replaying it. I highly doubt there's much if any security around the fan remote signals lol.
I did exactly the same thing for a different brand of DIP-switch-addressable remote-control fan back in 2016. It's been wonderful.
It wasn't that hard; I used gnuradio with an SDR to see what the remotes were sending and just pressed buttons and flipped switches until I figured out what all the bits were. There was no encryption whatsoever.
This annoys me too. My Casablanca fans have a wall switch which is hard wired to power only for on/off, but the fan and light controls are sent via a radio frequency signal. The most frustrating part of this, is that the RF transmitter inside the wall switch is battery operated. I have to unscrew the wall switch a couple times a year to get to the batteries.
Trust me, it could be worse. When we bought our house, the living room fan was hardwired with no switch. Literally you could only control it directly and hope it did what you asked it to do, there was no way to turn it off without turning off the entire circuit.
I suspect this is a code violation, but considering part of the lighting wiring in the basement had been done with speaker wire and automotive cabling, I don't think compliance was on the top of the previous owner's list.
As someone that designs battery powered RF devices. It's shocking an disheartening seeing stuff like that.
Things drawing an average of a few hundred microamps while the fan is running. Probably because it's blasting a keep alive packet once a second or so. It does that because a transceiver costs an extra 50 cents.
Do you feel any remorse for how this contributes to climate change?
Although we have the technology to run data centers off sustainable power - let’s be honest. Anthropic and OpenAI have not made any climate pledges that I know of.
I don’t see how a social network for AI bots benefits society at all. It’s a complete waste of a very valuable resource.
In other words, we’re burning the planet for this?
This feels like a fair question (perhaps not perfect wording, but no adhominem or disingenuity)
More broadly, we are overbuilding infra on highly inefficient silicon (at a time when designing silicon is easier than ever) and energy stacks _before_ the market is naturally driving it. (with assets that depreciate far faster than railroads). Just as China overbuilt Shenzhen
I have heard (unconfirmed) that the US is importing CNG engines from India for data center buildouts. I loved summers in my youth in Bombay and the parallax background have been great for photography, but the air is no fun to breathe (and does a kicker on life-expectancy to boot)
If we aren't asking these questions here, are they being asked? Don't bite the hand that feeds?
> I don’t see how a social network for AI bots benefits society at all. It’s a complete waste of a very valuable resource.
I don’t know what will happen, though I have ideas. I’m curious what hooking up my own with access to a (copy of) my dev environment and directing it to optimize by talking with other bots might result in.
But the fact that this is unique and new is sufficient justification in my opinion. AI is a transformative technology, and we should be focused on spending our energy and resources on improving and understanding it as fully as possible, as quickly as possible.
I think a lot of the people in positions of power in the AI industry think that AGI/superintelligence will solve the climate crisis, aging, scarcity, and many other tough problems by doing novel science. I hope they are correct.
I would be surprised if there many western journalists left in Iran…
Here is an excellent podcast from a Washington post journalist that was captured and held as a hostage - it’s called 544 days (that’s the amount of time he was jailed there)
Although some of the comments here have complained about the idea, I think they're missing the point. Although the skill and similar rules can be used to hide the fact you're using AI, it can also be used to make interacting with AI easier, i.e. when you're in a long coding session it can be quite daunting to be presented with so many questions and exhausting to look for the important decisions buried in an overwhelming amount of text. For those of us who are using AI to code, which is almost everyone now, this approach is likely to be very useful to reduce the cognitive overload.
reply